Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 66 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0787. Min Range: -9.0787
Max Act: 9.0787. Min Act: -0.1700
Data Index: 3012919 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0787. Min Range: -9.0787
Max Act: 9.0787. Min Act: -0.1700
Data Index: 10372 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.8287. Min Act: -0.1700
Data Index: 6931276 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.8287. Min Act: -0.1700
Data Index: 6692000 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.7037. Min Act: -0.1700
Data Index: 8544727 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.7037. Min Act: -0.1700
Data Index: 4071105 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.7037. Min Act: -0.1700
Data Index: 4563939 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.7037. Min Act: -0.1700
Data Index: 5180917 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.7037. Min Act: -0.1700
Data Index: 7649972 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.6412. Min Act: -0.1700
Data Index: 4158128 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.6412. Min Act: -0.1700
Data Index: 764467 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.6412. Min Act: -0.1700
Data Index: 3992404 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.5787. Min Act: -0.1700
Data Index: 1443048 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.5787. Min Act: -0.1700
Data Index: 675537 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.5787. Min Act: -0.1700
Data Index: 5225199 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.5787. Min Act: -0.1700
Data Index: 2977850 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.5162. Min Act: -0.1700
Data Index: 6849163 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.5162. Min Act: -0.1700
Data Index: 1550802 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.5162. Min Act: -0.1700
Data Index: 3678552 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0787. Min Range: -9.0787
Max Act: 8.5162. Min Act: -0.1700
Data Index: 3662396 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19