Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6382 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5869. Min Range: -6.5869
Max Act: 6.5869. Min Act: -0.1700
Data Index: 198720 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5869. Min Range: -6.5869
Max Act: 6.3056. Min Act: -0.1700
Data Index: 259540 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5869. Min Range: -6.5869
Max Act: 6.1806. Min Act: -0.1700
Data Index: 2583632 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5869. Min Range: -6.5869
Max Act: 6.1181. Min Act: -0.1700
Data Index: 2689440 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5869. Min Range: -6.5869
Max Act: 6.0869. Min Act: -0.1700
Data Index: 3179401 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5869. Min Range: -6.5869
Max Act: 6.0244. Min Act: -0.1700
Data Index: 5928876 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5869. Min Range: -6.5869
Max Act: 6.0556. Min Act: -0.1700
Data Index: 1590029 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5869. Min Range: -6.5869
Max Act: 6.0244. Min Act: -0.1700
Data Index: 3379720 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5869. Min Range: -6.5869
Max Act: 6.0244. Min Act: -0.1700
Data Index: 461752 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5869. Min Range: -6.5869
Max Act: 5.9619. Min Act: -0.1700
Data Index: 6070070 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5869. Min Range: -6.5869
Max Act: 6.0244. Min Act: -0.1700
Data Index: 1715641 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5869. Min Range: -6.5869
Max Act: 5.9619. Min Act: -0.1700
Data Index: 1924283 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5869. Min Range: -6.5869
Max Act: 5.9619. Min Act: -0.1700
Data Index: 6531972 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5869. Min Range: -6.5869
Max Act: 5.9306. Min Act: -0.1700
Data Index: 8327726 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5869. Min Range: -6.5869
Max Act: 5.9306. Min Act: -0.1700
Data Index: 6271180 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5869. Min Range: -6.5869
Max Act: 5.9306. Min Act: -0.1700
Data Index: 6146313 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5869. Min Range: -6.5869
Max Act: 5.8994. Min Act: -0.1700
Data Index: 5563834 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5869. Min Range: -6.5869
Max Act: 5.8994. Min Act: -0.1700
Data Index: 4547664 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5869. Min Range: -6.5869
Max Act: 5.8994. Min Act: -0.1700
Data Index: 6560575 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5869. Min Range: -6.5869
Max Act: 5.8994. Min Act: -0.1700
Data Index: 307320 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19