Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2524 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.9573. Min Act: -0.1700
Data Index: 707424 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.8948. Min Act: -0.1700
Data Index: 447574 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.5198. Min Act: -0.1700
Data Index: 3427065 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.5198. Min Act: -0.1700
Data Index: 4068256 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.3323. Min Act: -0.1700
Data Index: 282697 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.2073. Min Act: -0.1700
Data Index: 3569017 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.1448. Min Act: -0.1700
Data Index: 8334492 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.1448. Min Act: -0.1700
Data Index: 3107755 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.1448. Min Act: -0.1700
Data Index: 407771 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.0823. Min Act: -0.1700
Data Index: 7415485 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.0823. Min Act: -0.1700
Data Index: 6464457 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.1448. Min Act: -0.1700
Data Index: 2433409 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.0823. Min Act: -0.1700
Data Index: 4197048 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.0198. Min Act: -0.1700
Data Index: 712530 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9573. Min Range: -8.9573
Max Act: 8.0198. Min Act: -0.1700
Data Index: 7600912 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9573. Min Range: -8.9573
Max Act: 7.9573. Min Act: -0.1700
Data Index: 172150 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9573. Min Range: -8.9573
Max Act: 7.9573. Min Act: -0.1700
Data Index: 6459909 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9573. Min Range: -8.9573
Max Act: 7.9573. Min Act: -0.1700
Data Index: 948880 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9573. Min Range: -8.9573
Max Act: 7.8948. Min Act: -0.1700
Data Index: 1332788 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9573. Min Range: -8.9573
Max Act: 7.8948. Min Act: -0.1700
Data Index: 3016274 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19