Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.9334. Min Act: -0.1700
Data Index: 2036661 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.9022. Min Act: -0.1700
Data Index: 3567727 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.7772. Min Act: -0.1700
Data Index: 4462754 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.7772. Min Act: -0.1700
Data Index: 4585712 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.7459. Min Act: -0.1700
Data Index: 8734333 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.7459. Min Act: -0.1700
Data Index: 4543501 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.7147. Min Act: -0.1700
Data Index: 2919241 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.6834. Min Act: -0.1700
Data Index: 4461321 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.6834. Min Act: -0.1700
Data Index: 7620275 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.6522. Min Act: -0.1700
Data Index: 3869721 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.6522. Min Act: -0.1700
Data Index: 6476667 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.6209. Min Act: -0.1700
Data Index: 4165143 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.6209. Min Act: -0.1700
Data Index: 5691082 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.5897. Min Act: -0.1700
Data Index: 8734331 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.5897. Min Act: -0.1700
Data Index: 1636939 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.5897. Min Act: -0.1700
Data Index: 4416084 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.5584. Min Act: -0.1700
Data Index: 8103405 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.5584. Min Act: -0.1700
Data Index: 7313069 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.5272. Min Act: -0.1700
Data Index: 8646720 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9334. Min Range: -4.9334
Max Act: 4.5272. Min Act: -0.1700
Data Index: 5749180 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19