Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4820 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4299. Min Range: -6.4299
Max Act: 6.4299. Min Act: -0.1700
Data Index: 671088 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4299. Min Range: -6.4299
Max Act: 6.2112. Min Act: -0.1700
Data Index: 5448139 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4299. Min Range: -6.4299
Max Act: 6.0549. Min Act: -0.1700
Data Index: 8082900 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4299. Min Range: -6.4299
Max Act: 6.0549. Min Act: -0.1700
Data Index: 3975276 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.9924. Min Act: -0.1700
Data Index: 4516428 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.9924. Min Act: -0.1700
Data Index: 6213446 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.9612. Min Act: -0.1700
Data Index: 6920653 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.9612. Min Act: -0.1700
Data Index: 7046414 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.9612. Min Act: -0.1700
Data Index: 7904557 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.9612. Min Act: -0.1700
Data Index: 450855 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.9299. Min Act: -0.1700
Data Index: 1599141 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.9299. Min Act: -0.1700
Data Index: 8512497 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.8987. Min Act: -0.1700
Data Index: 5571896 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.8674. Min Act: -0.1700
Data Index: 5440574 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.8674. Min Act: -0.1700
Data Index: 1269100 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.8674. Min Act: -0.1700
Data Index: 6218413 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.8674. Min Act: -0.1700
Data Index: 1239779 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.8674. Min Act: -0.1700
Data Index: 5339610 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.8674. Min Act: -0.1700
Data Index: 4018989 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4299. Min Range: -6.4299
Max Act: 5.8362. Min Act: -0.1700
Data Index: 4297694 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19