Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4997 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.8843. Min Act: -0.1700
Data Index: 3204514 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.8843. Min Act: -0.1700
Data Index: 5950314 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.8218. Min Act: -0.1700
Data Index: 6189797 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.8218. Min Act: -0.1700
Data Index: 3732287 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7905. Min Act: -0.1700
Data Index: 2347100 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7592. Min Act: -0.1700
Data Index: 8664650 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7592. Min Act: -0.1700
Data Index: 87598 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7279. Min Act: -0.1700
Data Index: 8783571 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7279. Min Act: -0.1700
Data Index: 2479705 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6966. Min Act: -0.1700
Data Index: 2688830 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6966. Min Act: -0.1700
Data Index: 5309962 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6966. Min Act: -0.1700
Data Index: 6781308 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6966. Min Act: -0.1700
Data Index: 2023967 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7279. Min Act: -0.1700
Data Index: 5648076 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6653. Min Act: -0.1700
Data Index: 5404483 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6653. Min Act: -0.1700
Data Index: 615012 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6653. Min Act: -0.1700
Data Index: 157225 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6653. Min Act: -0.1700
Data Index: 2614610 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6653. Min Act: -0.1700
Data Index: 4585930 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6966. Min Act: -0.1700
Data Index: 7446854 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19