Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.8610. Min Act: -0.1700
Data Index: 6648547 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.8610. Min Act: -0.1700
Data Index: 4502822 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.7360. Min Act: -0.1700
Data Index: 7144212 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.7048. Min Act: -0.1700
Data Index: 6862740 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.7048. Min Act: -0.1700
Data Index: 7562431 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.6423. Min Act: -0.1700
Data Index: 5134200 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.6423. Min Act: -0.1700
Data Index: 5700816 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.6423. Min Act: -0.1700
Data Index: 7867637 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.6110. Min Act: -0.1700
Data Index: 3323645 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.6423. Min Act: -0.1700
Data Index: 6748975 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.6423. Min Act: -0.1700
Data Index: 2702833 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.6423. Min Act: -0.1700
Data Index: 1055733 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.6110. Min Act: -0.1700
Data Index: 6295120 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.6110. Min Act: -0.1700
Data Index: 4500196 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.6110. Min Act: -0.1700
Data Index: 1036823 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.5798. Min Act: -0.1700
Data Index: 4098720 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.6110. Min Act: -0.1700
Data Index: 5115271 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.5485. Min Act: -0.1700
Data Index: 3958743 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.5798. Min Act: -0.1700
Data Index: 2581481 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8610. Min Range: -4.8610
Max Act: 4.5798. Min Act: -0.1700
Data Index: 2603776 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19