Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4875 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3770. Min Range: -7.3770
Max Act: 7.3770. Min Act: -0.1700
Data Index: 6078784 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3770. Min Range: -7.3770
Max Act: 7.3457. Min Act: -0.1700
Data Index: 1779499 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3770. Min Range: -7.3770
Max Act: 7.1895. Min Act: -0.1700
Data Index: 3660377 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3770. Min Range: -7.3770
Max Act: 7.1270. Min Act: -0.1700
Data Index: 1437669 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.9082. Min Act: -0.1700
Data Index: 1982878 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.8457. Min Act: -0.1700
Data Index: 750750 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.8145. Min Act: -0.1700
Data Index: 962125 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.7832. Min Act: -0.1700
Data Index: 6078782 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.6895. Min Act: -0.1700
Data Index: 4286092 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.6582. Min Act: -0.1700
Data Index: 2240381 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.6270. Min Act: -0.1700
Data Index: 1888490 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.5957. Min Act: -0.1700
Data Index: 2038992 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.6270. Min Act: -0.1700
Data Index: 4578146 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.5332. Min Act: -0.1700
Data Index: 3657152 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.4707. Min Act: -0.1700
Data Index: 6453954 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.4707. Min Act: -0.1700
Data Index: 5246183 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.4707. Min Act: -0.1700
Data Index: 989996 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.5020. Min Act: -0.1700
Data Index: 458842 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.4707. Min Act: -0.1700
Data Index: 6149294 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3770. Min Range: -7.3770
Max Act: 6.4082. Min Act: -0.1700
Data Index: 4108179 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19