Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.7437. Min Act: -0.1700
Data Index: 523426 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.7437. Min Act: -0.1700
Data Index: 6859053 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.7437. Min Act: -0.1700
Data Index: 5117866 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.7437. Min Act: -0.1700
Data Index: 2515868 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.7004. Min Act: -0.1700
Data Index: 2988112 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6918. Min Act: -0.1700
Data Index: 7525711 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6831. Min Act: -0.1700
Data Index: 2684151 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6657. Min Act: -0.1700
Data Index: 768818 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6483. Min Act: -0.1700
Data Index: 2475478 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6483. Min Act: -0.1700
Data Index: 2475479 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6483. Min Act: -0.1700
Data Index: 7976616 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6396. Min Act: -0.1700
Data Index: 337706 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6396. Min Act: -0.1700
Data Index: 7976615 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6396. Min Act: -0.1700
Data Index: 364830 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6396. Min Act: -0.1700
Data Index: 2059679 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6222. Min Act: -0.1700
Data Index: 364828 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6222. Min Act: -0.1700
Data Index: 4855315 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6135. Min Act: -0.1700
Data Index: 1851524 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6135. Min Act: -0.1700
Data Index: 3764645 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7437. Min Range: -1.7437
Max Act: 1.6047. Min Act: -0.1700
Data Index: 1485006 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19