Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.9566. Min Act: -0.1700
Data Index: 2503688 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.8004. Min Act: -0.1700
Data Index: 3299538 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.7066. Min Act: -0.1700
Data Index: 6594741 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.6129. Min Act: -0.1700
Data Index: 6976597 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.5504. Min Act: -0.1700
Data Index: 7693799 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.5191. Min Act: -0.1700
Data Index: 3169143 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.5504. Min Act: -0.1700
Data Index: 7855371 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.4879. Min Act: -0.1700
Data Index: 4640994 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.4566. Min Act: -0.1700
Data Index: 7731608 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.4254. Min Act: -0.1700
Data Index: 4040388 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.3941. Min Act: -0.1700
Data Index: 2480972 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.4254. Min Act: -0.1700
Data Index: 1530351 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.4254. Min Act: -0.1700
Data Index: 4384227 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.3941. Min Act: -0.1700
Data Index: 8069043 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.4254. Min Act: -0.1700
Data Index: 3187720 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.3629. Min Act: -0.1700
Data Index: 4895258 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.3629. Min Act: -0.1700
Data Index: 6999873 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.3629. Min Act: -0.1700
Data Index: 5532772 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.3629. Min Act: -0.1700
Data Index: 8617268 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9566. Min Range: -6.9566
Max Act: 6.3316. Min Act: -0.1700
Data Index: 572564 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19