Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5745 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3221. Min Range: -6.3221
Max Act: 6.3221. Min Act: -0.1700
Data Index: 5923986 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3221. Min Range: -6.3221
Max Act: 6.1659. Min Act: -0.1700
Data Index: 734394 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3221. Min Range: -6.3221
Max Act: 6.1346. Min Act: -0.1700
Data Index: 4562315 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.9784. Min Act: -0.1700
Data Index: 711718 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.9471. Min Act: -0.1700
Data Index: 465963 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.9471. Min Act: -0.1700
Data Index: 8194907 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.9159. Min Act: -0.1700
Data Index: 680695 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8846. Min Act: -0.1700
Data Index: 5744657 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8846. Min Act: -0.1700
Data Index: 3245079 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8846. Min Act: -0.1700
Data Index: 2027343 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8846. Min Act: -0.1700
Data Index: 488073 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8846. Min Act: -0.1700
Data Index: 711433 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8846. Min Act: -0.1700
Data Index: 449627 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8534. Min Act: -0.1700
Data Index: 7050896 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8534. Min Act: -0.1700
Data Index: 5834316 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8221. Min Act: -0.1700
Data Index: 5129820 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8534. Min Act: -0.1700
Data Index: 6100334 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8534. Min Act: -0.1700
Data Index: 2832419 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8221. Min Act: -0.1700
Data Index: 882770 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3221. Min Range: -6.3221
Max Act: 5.8221. Min Act: -0.1700
Data Index: 815582 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19