Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.7346. Min Act: -0.1700
Data Index: 8462880 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.6096. Min Act: -0.1700
Data Index: 5080478 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.4846. Min Act: -0.1700
Data Index: 2287500 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.4221. Min Act: -0.1700
Data Index: 2849103 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.3596. Min Act: -0.1700
Data Index: 3684280 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.3596. Min Act: -0.1700
Data Index: 1751415 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.3596. Min Act: -0.1700
Data Index: 7838698 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.2971. Min Act: -0.1700
Data Index: 6789369 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.2971. Min Act: -0.1700
Data Index: 3684281 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.2346. Min Act: -0.1700
Data Index: 5938383 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.2346. Min Act: -0.1700
Data Index: 3320942 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.2346. Min Act: -0.1700
Data Index: 3371746 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.1721. Min Act: -0.1700
Data Index: 6755675 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.1096. Min Act: -0.1700
Data Index: 205643 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.1096. Min Act: -0.1700
Data Index: 3332554 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.0471. Min Act: -0.1700
Data Index: 1161693 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.1096. Min Act: -0.1700
Data Index: 7579093 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.0471. Min Act: -0.1700
Data Index: 8238289 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.0471. Min Act: -0.1700
Data Index: 3427988 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7346. Min Range: -9.7346
Max Act: 9.0471. Min Act: -0.1700
Data Index: 2357596 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19