Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4280 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.6442. Min Act: -0.1700
Data Index: 3018298 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.5504. Min Act: -0.1700
Data Index: 5199754 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.5192. Min Act: -0.1700
Data Index: 8611868 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.4567. Min Act: -0.1700
Data Index: 3979437 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.4567. Min Act: -0.1700
Data Index: 876535 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.3942. Min Act: -0.1700
Data Index: 6495826 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.3942. Min Act: -0.1700
Data Index: 7870613 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.3004. Min Act: -0.1700
Data Index: 6975423 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.3004. Min Act: -0.1700
Data Index: 5054761 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.2379. Min Act: -0.1700
Data Index: 7735006 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.1754. Min Act: -0.1700
Data Index: 5045356 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.1754. Min Act: -0.1700
Data Index: 2451831 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.1754. Min Act: -0.1700
Data Index: 4628295 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.1442. Min Act: -0.1700
Data Index: 4321511 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.1129. Min Act: -0.1700
Data Index: 3407345 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.1129. Min Act: -0.1700
Data Index: 287533 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.0817. Min Act: -0.1700
Data Index: 6027386 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.0817. Min Act: -0.1700
Data Index: 6460369 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.0817. Min Act: -0.1700
Data Index: 2908161 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6442. Min Range: -5.6442
Max Act: 5.0817. Min Act: -0.1700
Data Index: 1158027 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19