Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 16.9798. Min Range: -16.9798
Max Act: 16.9798. Min Act: -0.1700
Data Index: 6612117 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.9798. Min Range: -16.9798
Max Act: 16.9798. Min Act: -0.1700
Data Index: 6612112 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.9173. Min Act: -0.1699
Data Index: 5876948 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.9173. Min Act: -0.1700
Data Index: 889822 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.7923. Min Act: -0.1700
Data Index: 7024966 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.7298. Min Act: -0.1700
Data Index: 7738606 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.6673. Min Act: -0.1700
Data Index: 3108585 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.6048. Min Act: -0.1700
Data Index: 4587385 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.5423. Min Act: -0.1700
Data Index: 4587386 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.6048. Min Act: -0.1700
Data Index: 6612116 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.5423. Min Act: -0.1700
Data Index: 889827 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.6048. Min Act: -0.1700
Data Index: 6612111 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.6048. Min Act: -0.1700
Data Index: 8686170 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.5423. Min Act: -0.1700
Data Index: 1613361 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.5423. Min Act: -0.1700
Data Index: 8686183 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.4798. Min Act: -0.1700
Data Index: 5326619 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.4173. Min Act: -0.1700
Data Index: 2462223 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.3548. Min Act: -0.1700
Data Index: 5994297 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.2923. Min Act: -0.1700
Data Index: 5153755 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.9798. Min Range: -16.9798
Max Act: 15.2923. Min Act: -0.1700
Data Index: 5996697 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19