Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1020. Min Range: -7.1020
Max Act: 7.1020. Min Act: -0.1700
Data Index: 603276 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.7895. Min Act: -0.1700
Data Index: 1933949 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.7270. Min Act: -0.1700
Data Index: 8491793 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.6645. Min Act: -0.1700
Data Index: 6040176 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.6645. Min Act: -0.1700
Data Index: 5145158 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.5395. Min Act: -0.1700
Data Index: 3887642 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.4770. Min Act: -0.1700
Data Index: 5159025 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.4770. Min Act: -0.1700
Data Index: 4885734 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.4145. Min Act: -0.1700
Data Index: 7116323 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.4145. Min Act: -0.1700
Data Index: 3289048 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.3832. Min Act: -0.1700
Data Index: 5813174 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.3832. Min Act: -0.1700
Data Index: 7348891 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.3520. Min Act: -0.1700
Data Index: 5190317 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.3832. Min Act: -0.1700
Data Index: 6380353 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.3520. Min Act: -0.1700
Data Index: 2766225 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.3832. Min Act: -0.1700
Data Index: 2838797 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.3520. Min Act: -0.1700
Data Index: 635020 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.3207. Min Act: -0.1700
Data Index: 2013260 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.2582. Min Act: -0.1700
Data Index: 2272724 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1020. Min Range: -7.1020
Max Act: 6.2582. Min Act: -0.1700
Data Index: 2272721 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19