Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5420 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8304. Min Range: -7.8304
Max Act: 7.8304. Min Act: -0.1700
Data Index: 5888838 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8304. Min Range: -7.8304
Max Act: 7.5179. Min Act: -0.1700
Data Index: 6051599 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8304. Min Range: -7.8304
Max Act: 7.2991. Min Act: -0.1700
Data Index: 7661411 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8304. Min Range: -7.8304
Max Act: 7.2054. Min Act: -0.1700
Data Index: 6512595 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8304. Min Range: -7.8304
Max Act: 7.0804. Min Act: -0.1700
Data Index: 4416759 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8304. Min Range: -7.8304
Max Act: 7.0804. Min Act: -0.1700
Data Index: 6439100 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8304. Min Range: -7.8304
Max Act: 7.0179. Min Act: -0.1700
Data Index: 4692822 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8304. Min Range: -7.8304
Max Act: 7.0491. Min Act: -0.1700
Data Index: 8050742 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8304. Min Range: -7.8304
Max Act: 7.0179. Min Act: -0.1700
Data Index: 675796 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8304. Min Range: -7.8304
Max Act: 7.0179. Min Act: -0.1700
Data Index: 4297063 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8304. Min Range: -7.8304
Max Act: 7.0179. Min Act: -0.1700
Data Index: 6239680 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8304. Min Range: -7.8304
Max Act: 6.9554. Min Act: -0.1700
Data Index: 1760387 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8304. Min Range: -7.8304
Max Act: 6.8929. Min Act: -0.1700
Data Index: 8772290 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8304. Min Range: -7.8304
Max Act: 6.8616. Min Act: -0.1700
Data Index: 2067899 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8304. Min Range: -7.8304
Max Act: 6.8304. Min Act: -0.1700
Data Index: 6395399 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8304. Min Range: -7.8304
Max Act: 6.7991. Min Act: -0.1700
Data Index: 1505882 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8304. Min Range: -7.8304
Max Act: 6.7991. Min Act: -0.1700
Data Index: 6540535 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8304. Min Range: -7.8304
Max Act: 6.8616. Min Act: -0.1700
Data Index: 5905341 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8304. Min Range: -7.8304
Max Act: 6.8304. Min Act: -0.1700
Data Index: 5274232 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8304. Min Range: -7.8304
Max Act: 6.7991. Min Act: -0.1700
Data Index: 3572752 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19