Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 891 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.8179. Min Act: -0.1700
Data Index: 4358602 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.8179. Min Act: -0.1700
Data Index: 675676 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.8179. Min Act: -0.1700
Data Index: 8826108 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.7554. Min Act: -0.1700
Data Index: 6610210 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.6929. Min Act: -0.1700
Data Index: 2015483 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.6929. Min Act: -0.1700
Data Index: 1689342 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.5991. Min Act: -0.1700
Data Index: 6379838 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.5991. Min Act: -0.1700
Data Index: 7460840 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.5679. Min Act: -0.1700
Data Index: 6502210 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.5991. Min Act: -0.1700
Data Index: 8807689 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.5679. Min Act: -0.1700
Data Index: 3288016 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.5679. Min Act: -0.1700
Data Index: 1028569 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.5366. Min Act: -0.1700
Data Index: 696273 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.5366. Min Act: -0.1700
Data Index: 504983 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.5366. Min Act: -0.1700
Data Index: 2311229 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.5054. Min Act: -0.1700
Data Index: 8431142 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.5054. Min Act: -0.1700
Data Index: 4742961 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.4741. Min Act: -0.1700
Data Index: 8593972 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.4429. Min Act: -0.1700
Data Index: 5656354 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8179. Min Range: -7.8179
Max Act: 7.4741. Min Act: -0.1700
Data Index: 7228992 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19