Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4186 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1019. Min Range: -8.1019
Max Act: 8.1019. Min Act: -0.1700
Data Index: 6294389 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.9144. Min Act: -0.1700
Data Index: 3266180 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.9144. Min Act: -0.1700
Data Index: 5083928 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.8832. Min Act: -0.1700
Data Index: 17140 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.8519. Min Act: -0.1700
Data Index: 5237623 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.8519. Min Act: -0.1700
Data Index: 8261621 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.7894. Min Act: -0.1700
Data Index: 3604598 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.7894. Min Act: -0.1700
Data Index: 8072247 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.7894. Min Act: -0.1700
Data Index: 2330170 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.7582. Min Act: -0.1700
Data Index: 7018330 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.7269. Min Act: -0.1700
Data Index: 6215061 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6644. Min Act: -0.1700
Data Index: 6376469 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6644. Min Act: -0.1700
Data Index: 1663531 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6019. Min Act: -0.1700
Data Index: 3452809 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6332. Min Act: -0.1700
Data Index: 573715 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6019. Min Act: -0.1700
Data Index: 6130177 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6332. Min Act: -0.1700
Data Index: 1759781 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6332. Min Act: -0.1700
Data Index: 836586 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6019. Min Act: -0.1700
Data Index: 3386237 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.5707. Min Act: -0.1700
Data Index: 1459630 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19