Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.8262. Min Act: -0.1700
Data Index: 366407 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.7637. Min Act: -0.1700
Data Index: 5806541 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.4512. Min Act: -0.1700
Data Index: 1142345 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.3887. Min Act: -0.1700
Data Index: 3223409 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.3262. Min Act: -0.1700
Data Index: 7885780 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.3574. Min Act: -0.1700
Data Index: 6164857 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.3574. Min Act: -0.1700
Data Index: 5737060 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.2949. Min Act: -0.1700
Data Index: 3677187 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.2949. Min Act: -0.1700
Data Index: 968217 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.2324. Min Act: -0.1700
Data Index: 1574033 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.2324. Min Act: -0.1700
Data Index: 4904423 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.2324. Min Act: -0.1700
Data Index: 2712033 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.2324. Min Act: -0.1700
Data Index: 1922517 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.2012. Min Act: -0.1700
Data Index: 6053683 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.2012. Min Act: -0.1700
Data Index: 2015378 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.1699. Min Act: -0.1700
Data Index: 2002682 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.2012. Min Act: -0.1700
Data Index: 5409785 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.1699. Min Act: -0.1700
Data Index: 6452876 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.1699. Min Act: -0.1700
Data Index: 932381 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8262. Min Range: -6.8262
Max Act: 6.1699. Min Act: -0.1700
Data Index: 4663585 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19