Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.8300. Min Act: -0.1700
Data Index: 5755465 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.8300. Min Act: -0.1700
Data Index: 2379786 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.7050. Min Act: -0.1700
Data Index: 6764934 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.7050. Min Act: -0.1700
Data Index: 253997 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.6737. Min Act: -0.1699
Data Index: 5725505 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.6425. Min Act: -0.1700
Data Index: 6546572 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.6112. Min Act: -0.1700
Data Index: 5774721 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5800. Min Act: -0.1700
Data Index: 8738940 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5800. Min Act: -0.1699
Data Index: 1224984 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.6112. Min Act: -0.1695
Data Index: 5755463 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5487. Min Act: -0.1700
Data Index: 901903 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5487. Min Act: -0.1700
Data Index: 7863378 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5487. Min Act: -0.1700
Data Index: 950438 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5175. Min Act: -0.1700
Data Index: 62875 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5487. Min Act: -0.1700
Data Index: 216220 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5487. Min Act: -0.1700
Data Index: 7289068 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5175. Min Act: -0.1700
Data Index: 1503008 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5175. Min Act: -0.1700
Data Index: 5000309 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5175. Min Act: -0.1700
Data Index: 2503752 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5175. Min Act: -0.1700
Data Index: 4198204 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19