Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 87 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.6959. Min Act: -0.1700
Data Index: 574456 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.4459. Min Act: -0.1700
Data Index: 6350745 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.4459. Min Act: -0.1700
Data Index: 1541213 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.4459. Min Act: -0.1700
Data Index: 6569031 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.3834. Min Act: -0.1700
Data Index: 4022643 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.3834. Min Act: -0.1700
Data Index: 3237737 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.3209. Min Act: -0.1700
Data Index: 1095514 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.3209. Min Act: -0.1700
Data Index: 2390269 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.3209. Min Act: -0.1700
Data Index: 1023611 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.3209. Min Act: -0.1700
Data Index: 5671113 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.3209. Min Act: -0.1700
Data Index: 370102 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.2584. Min Act: -0.1700
Data Index: 6259294 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.1959. Min Act: -0.1700
Data Index: 456726 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.1959. Min Act: -0.1700
Data Index: 260466 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.0709. Min Act: -0.1700
Data Index: 1685516 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.1334. Min Act: -0.1700
Data Index: 5720102 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.1334. Min Act: -0.1700
Data Index: 8350936 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.0709. Min Act: -0.1700
Data Index: 6118007 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.0709. Min Act: -0.1700
Data Index: 1093100 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6959. Min Range: -9.6959
Max Act: 9.0709. Min Act: -0.1700
Data Index: 6711708 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19