Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 656 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5877. Min Range: -7.5877
Max Act: 7.5877. Min Act: -0.1700
Data Index: 8471166 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5877. Min Range: -7.5877
Max Act: 7.2752. Min Act: -0.1700
Data Index: 5578270 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5877. Min Range: -7.5877
Max Act: 7.0877. Min Act: -0.1700
Data Index: 8310169 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5877. Min Range: -7.5877
Max Act: 7.0252. Min Act: -0.1700
Data Index: 8333515 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.9627. Min Act: -0.1700
Data Index: 1231983 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.8689. Min Act: -0.1700
Data Index: 8353255 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.8689. Min Act: -0.1700
Data Index: 3825015 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.8689. Min Act: -0.1700
Data Index: 4605649 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.8377. Min Act: -0.1700
Data Index: 6819427 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.8064. Min Act: -0.1700
Data Index: 7098428 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.7439. Min Act: -0.1700
Data Index: 7583698 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.7439. Min Act: -0.1700
Data Index: 6864136 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.7127. Min Act: -0.1700
Data Index: 632426 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.7439. Min Act: -0.1700
Data Index: 756780 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.7127. Min Act: -0.1700
Data Index: 3154766 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.7127. Min Act: -0.1700
Data Index: 3519220 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.7127. Min Act: -0.1700
Data Index: 3276949 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.7127. Min Act: -0.1700
Data Index: 5930994 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.6814. Min Act: -0.1700
Data Index: 3854512 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5877. Min Range: -7.5877
Max Act: 6.6814. Min Act: -0.1700
Data Index: 1931500 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19