Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4970 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.9360. Min Act: -0.1700
Data Index: 4381885 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.4985. Min Act: -0.1700
Data Index: 986443 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.4048. Min Act: -0.1700
Data Index: 8048029 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.4048. Min Act: -0.1700
Data Index: 3869109 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.3735. Min Act: -0.1700
Data Index: 8432362 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.2798. Min Act: -0.1700
Data Index: 7534736 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.2485. Min Act: -0.1700
Data Index: 4231954 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.2173. Min Act: -0.1700
Data Index: 8141990 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.2173. Min Act: -0.1700
Data Index: 2736029 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.2485. Min Act: -0.1700
Data Index: 6339714 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.1548. Min Act: -0.1700
Data Index: 6109129 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.1860. Min Act: -0.1700
Data Index: 5526591 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.1548. Min Act: -0.1700
Data Index: 5237942 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.1235. Min Act: -0.1700
Data Index: 3125300 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.1235. Min Act: -0.1700
Data Index: 4166236 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.1235. Min Act: -0.1700
Data Index: 4538810 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.1235. Min Act: -0.1700
Data Index: 1739977 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.0610. Min Act: -0.1700
Data Index: 3853786 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.0923. Min Act: -0.1700
Data Index: 6884416 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9360. Min Range: -6.9360
Max Act: 6.0610. Min Act: -0.1700
Data Index: 6102162 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19