Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 789 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.2378. Min Act: -0.1700
Data Index: 5180605 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.1753. Min Act: -0.1700
Data Index: 7937515 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.1440. Min Act: -0.1700
Data Index: 5680419 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.1440. Min Act: -0.1700
Data Index: 5289513 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.1440. Min Act: -0.1700
Data Index: 1371282 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.1128. Min Act: -0.1700
Data Index: 6410881 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.1128. Min Act: -0.1700
Data Index: 2043243 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.1440. Min Act: -0.1700
Data Index: 797468 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.1440. Min Act: -0.1700
Data Index: 4632034 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.0815. Min Act: -0.1700
Data Index: 7949455 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.0815. Min Act: -0.1700
Data Index: 5065472 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.1128. Min Act: -0.1700
Data Index: 1750195 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.0815. Min Act: -0.1700
Data Index: 3804853 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.0815. Min Act: -0.1700
Data Index: 6040208 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.0503. Min Act: -0.1700
Data Index: 7588871 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.0503. Min Act: -0.1700
Data Index: 2477808 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.0503. Min Act: -0.1700
Data Index: 3761811 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.0503. Min Act: -0.1700
Data Index: 3556519 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.0503. Min Act: -0.1700
Data Index: 5220429 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2378. Min Range: -4.2378
Max Act: 4.0503. Min Act: -0.1700
Data Index: 3351698 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19