Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4428 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6207. Min Range: -9.6207
Max Act: 9.6207. Min Act: -0.1700
Data Index: 7235628 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6207. Min Range: -9.6207
Max Act: 9.4957. Min Act: -0.1700
Data Index: 8315616 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6207. Min Range: -9.6207
Max Act: 9.4332. Min Act: -0.1700
Data Index: 5631654 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6207. Min Range: -9.6207
Max Act: 9.3082. Min Act: -0.1700
Data Index: 395550 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6207. Min Range: -9.6207
Max Act: 9.3082. Min Act: -0.1700
Data Index: 6397769 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6207. Min Range: -9.6207
Max Act: 9.3082. Min Act: -0.1700
Data Index: 7112129 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6207. Min Range: -9.6207
Max Act: 9.2457. Min Act: -0.1700
Data Index: 5266039 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6207. Min Range: -9.6207
Max Act: 9.2457. Min Act: -0.1700
Data Index: 5043321 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6207. Min Range: -9.6207
Max Act: 9.1207. Min Act: -0.1700
Data Index: 4759933 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6207. Min Range: -9.6207
Max Act: 9.0582. Min Act: -0.1700
Data Index: 1387926 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6207. Min Range: -9.6207
Max Act: 8.9957. Min Act: -0.1700
Data Index: 1667239 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6207. Min Range: -9.6207
Max Act: 8.9332. Min Act: -0.1700
Data Index: 2663151 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6207. Min Range: -9.6207
Max Act: 8.8707. Min Act: -0.1700
Data Index: 176578 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6207. Min Range: -9.6207
Max Act: 8.9332. Min Act: -0.1700
Data Index: 3317079 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6207. Min Range: -9.6207
Max Act: 8.9332. Min Act: -0.1700
Data Index: 4289242 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6207. Min Range: -9.6207
Max Act: 8.9332. Min Act: -0.1700
Data Index: 7771859 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6207. Min Range: -9.6207
Max Act: 8.8707. Min Act: -0.1700
Data Index: 469890 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6207. Min Range: -9.6207
Max Act: 8.9332. Min Act: -0.1700
Data Index: 6181953 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6207. Min Range: -9.6207
Max Act: 8.8707. Min Act: -0.1700
Data Index: 4063999 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6207. Min Range: -9.6207
Max Act: 8.8707. Min Act: -0.1700
Data Index: 808833 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19