Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.9238. Min Act: -0.1700
Data Index: 4414921 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.7988. Min Act: -0.1700
Data Index: 7294667 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.7675. Min Act: -0.1700
Data Index: 6418848 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.7050. Min Act: -0.1700
Data Index: 8757927 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.6425. Min Act: -0.1700
Data Index: 2247734 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.6425. Min Act: -0.1700
Data Index: 8250803 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.6113. Min Act: -0.1700
Data Index: 8456604 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.6113. Min Act: -0.1700
Data Index: 837406 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.5488. Min Act: -0.1700
Data Index: 4749282 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.5800. Min Act: -0.1700
Data Index: 3341836 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.5800. Min Act: -0.1700
Data Index: 5114161 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.5488. Min Act: -0.1700
Data Index: 7713239 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.5488. Min Act: -0.1700
Data Index: 287341 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.5175. Min Act: -0.1700
Data Index: 1808577 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.5175. Min Act: -0.1700
Data Index: 6611663 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.5175. Min Act: -0.1700
Data Index: 4563543 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.4863. Min Act: -0.1700
Data Index: 7439924 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.4863. Min Act: -0.1700
Data Index: 4775326 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.4550. Min Act: -0.1700
Data Index: 1756358 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9238. Min Range: -6.9238
Max Act: 6.4550. Min Act: -0.1700
Data Index: 4359823 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19