Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2200 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0360. Min Range: -7.0360
Max Act: 7.0360. Min Act: -0.1700
Data Index: 7584418 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.9423. Min Act: -0.1700
Data Index: 4020114 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.9110. Min Act: -0.1700
Data Index: 8115156 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.8485. Min Act: -0.1700
Data Index: 1635303 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.8485. Min Act: -0.1700
Data Index: 2997741 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.8173. Min Act: -0.1700
Data Index: 2242489 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.8173. Min Act: -0.1700
Data Index: 6482800 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.7860. Min Act: -0.1700
Data Index: 7483435 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.7860. Min Act: -0.1700
Data Index: 1756686 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.7548. Min Act: -0.1700
Data Index: 4735760 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.7548. Min Act: -0.1700
Data Index: 567919 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.7548. Min Act: -0.1700
Data Index: 5070934 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.7548. Min Act: -0.1700
Data Index: 3830557 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.7235. Min Act: -0.1700
Data Index: 2684291 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.7235. Min Act: -0.1700
Data Index: 1878876 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.7235. Min Act: -0.1700
Data Index: 2168233 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.7235. Min Act: -0.1700
Data Index: 5738010 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.6923. Min Act: -0.1700
Data Index: 8115154 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.6610. Min Act: -0.1700
Data Index: 5341944 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0360. Min Range: -7.0360
Max Act: 6.6610. Min Act: -0.1700
Data Index: 7103733 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19