Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1347 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1147. Min Range: -7.1147
Max Act: 7.1147. Min Act: -0.1700
Data Index: 3285108 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1147. Min Range: -7.1147
Max Act: 7.1147. Min Act: -0.1700
Data Index: 6520365 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1147. Min Range: -7.1147
Max Act: 7.0522. Min Act: -0.1700
Data Index: 288696 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1147. Min Range: -7.1147
Max Act: 7.0522. Min Act: -0.1700
Data Index: 2466357 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1147. Min Range: -7.1147
Max Act: 7.0209. Min Act: -0.1700
Data Index: 4477144 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.9897. Min Act: -0.1700
Data Index: 1727623 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.9584. Min Act: -0.1700
Data Index: 1890169 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.9272. Min Act: -0.1700
Data Index: 4589962 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.8959. Min Act: -0.1700
Data Index: 1384047 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.8959. Min Act: -0.1700
Data Index: 3645984 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.8647. Min Act: -0.1700
Data Index: 7301989 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.8647. Min Act: -0.1700
Data Index: 4057952 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.8334. Min Act: -0.1700
Data Index: 7220797 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.8334. Min Act: -0.1700
Data Index: 2158414 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.8334. Min Act: -0.1700
Data Index: 2158070 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.8334. Min Act: -0.1700
Data Index: 6240057 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.8334. Min Act: -0.1700
Data Index: 1858386 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.8334. Min Act: -0.1700
Data Index: 6418484 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.8022. Min Act: -0.1700
Data Index: 1078645 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1147. Min Range: -7.1147
Max Act: 6.7709. Min Act: -0.1700
Data Index: 6889617 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19