Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4267 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.7958. Min Act: -0.1700
Data Index: 419236 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.7645. Min Act: -0.1700
Data Index: 6804075 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.7333. Min Act: -0.1700
Data Index: 475201 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.6083. Min Act: -0.1700
Data Index: 5132268 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5770. Min Act: -0.1700
Data Index: 4855419 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5770. Min Act: -0.1700
Data Index: 2622828 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5458. Min Act: -0.1700
Data Index: 6919578 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5770. Min Act: -0.1700
Data Index: 2056738 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.4833. Min Act: -0.1700
Data Index: 5758682 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.4520. Min Act: -0.1700
Data Index: 2802868 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.4833. Min Act: -0.1700
Data Index: 5640769 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.4520. Min Act: -0.1700
Data Index: 8309966 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.4520. Min Act: -0.1700
Data Index: 4383036 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.4520. Min Act: -0.1700
Data Index: 2453134 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.4208. Min Act: -0.1700
Data Index: 4006949 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.3583. Min Act: -0.1700
Data Index: 4333521 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.3583. Min Act: -0.1700
Data Index: 6262981 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.3895. Min Act: -0.1700
Data Index: 3468570 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.3895. Min Act: -0.1700
Data Index: 1602666 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.3895. Min Act: -0.1700
Data Index: 5049662 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19