Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5467 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2471. Min Range: -6.2471
Max Act: 6.2471. Min Act: -0.1700
Data Index: 1872969 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2471. Min Range: -6.2471
Max Act: 6.2159. Min Act: -0.1700
Data Index: 4729781 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2471. Min Range: -6.2471
Max Act: 6.1846. Min Act: -0.1700
Data Index: 8323977 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2471. Min Range: -6.2471
Max Act: 6.1534. Min Act: -0.1700
Data Index: 7630160 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2471. Min Range: -6.2471
Max Act: 6.1534. Min Act: -0.1700
Data Index: 7628448 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2471. Min Range: -6.2471
Max Act: 6.1221. Min Act: -0.1700
Data Index: 8156550 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2471. Min Range: -6.2471
Max Act: 6.0909. Min Act: -0.1700
Data Index: 561667 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2471. Min Range: -6.2471
Max Act: 6.0596. Min Act: -0.1700
Data Index: 7743493 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2471. Min Range: -6.2471
Max Act: 5.9346. Min Act: -0.1700
Data Index: 1739758 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2471. Min Range: -6.2471
Max Act: 5.9659. Min Act: -0.1700
Data Index: 3517701 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2471. Min Range: -6.2471
Max Act: 5.9659. Min Act: -0.1700
Data Index: 4550917 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2471. Min Range: -6.2471
Max Act: 5.9034. Min Act: -0.1700
Data Index: 1821849 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2471. Min Range: -6.2471
Max Act: 5.9034. Min Act: -0.1700
Data Index: 7176531 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2471. Min Range: -6.2471
Max Act: 5.8721. Min Act: -0.1700
Data Index: 8073554 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2471. Min Range: -6.2471
Max Act: 5.8721. Min Act: -0.1700
Data Index: 1011384 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2471. Min Range: -6.2471
Max Act: 5.8721. Min Act: -0.1700
Data Index: 390129 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2471. Min Range: -6.2471
Max Act: 5.8409. Min Act: -0.1700
Data Index: 7429389 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2471. Min Range: -6.2471
Max Act: 5.8409. Min Act: -0.1700
Data Index: 2655347 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2471. Min Range: -6.2471
Max Act: 5.8096. Min Act: -0.1700
Data Index: 4576525 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2471. Min Range: -6.2471
Max Act: 5.8409. Min Act: -0.1700
Data Index: 1661881 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19