Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2809 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.7209. Min Act: -0.1700
Data Index: 719090 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.5334. Min Act: -0.1700
Data Index: 1365317 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.4084. Min Act: -0.1700
Data Index: 6911544 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.3147. Min Act: -0.1700
Data Index: 3927768 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.3459. Min Act: -0.1700
Data Index: 1065377 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.3147. Min Act: -0.1700
Data Index: 1580120 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.3147. Min Act: -0.1700
Data Index: 1607733 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.2522. Min Act: -0.1700
Data Index: 2357573 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.1897. Min Act: -0.1700
Data Index: 3959659 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.2209. Min Act: -0.1700
Data Index: 4002354 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.1897. Min Act: -0.1700
Data Index: 5528693 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.1584. Min Act: -0.1700
Data Index: 6268262 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.1272. Min Act: -0.1700
Data Index: 2028264 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.0959. Min Act: -0.1700
Data Index: 8086897 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.0959. Min Act: -0.1700
Data Index: 289187 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.0959. Min Act: -0.1700
Data Index: 1149889 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.0959. Min Act: -0.1700
Data Index: 8448821 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.0334. Min Act: -0.1700
Data Index: 6550028 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.0647. Min Act: -0.1700
Data Index: 5655530 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7209. Min Range: -7.7209
Max Act: 7.0334. Min Act: -0.1700
Data Index: 4887266 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19