Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0787. Min Range: -6.0787
Max Act: 6.0787. Min Act: -0.1700
Data Index: 5375317 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.9850. Min Act: -0.1700
Data Index: 4646182 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.8600. Min Act: -0.1700
Data Index: 1677410 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.8600. Min Act: -0.1700
Data Index: 4969653 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.8287. Min Act: -0.1700
Data Index: 1039345 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.7975. Min Act: -0.1700
Data Index: 4510758 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.7037. Min Act: -0.1700
Data Index: 7096240 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.5475. Min Act: -0.1700
Data Index: 3650117 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.5475. Min Act: -0.1700
Data Index: 5688699 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.5162. Min Act: -0.1700
Data Index: 2266244 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.4850. Min Act: -0.1700
Data Index: 5195211 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.4537. Min Act: -0.1700
Data Index: 1632229 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.4537. Min Act: -0.1700
Data Index: 4109017 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.4537. Min Act: -0.1700
Data Index: 3731975 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.4537. Min Act: -0.1700
Data Index: 4403440 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.4537. Min Act: -0.1700
Data Index: 7898957 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.4225. Min Act: -0.1700
Data Index: 8540093 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.4225. Min Act: -0.1700
Data Index: 573514 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.3912. Min Act: -0.1700
Data Index: 5312601 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.3600. Min Act: -0.1700
Data Index: 3541567 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19