Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1379 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.5411. Min Act: -0.1700
Data Index: 8002131 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.5411. Min Act: -0.1700
Data Index: 270719 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.5411. Min Act: -0.1700
Data Index: 1447351 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.5411. Min Act: -0.1700
Data Index: 218572 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4786. Min Act: -0.1700
Data Index: 4189523 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4786. Min Act: -0.1700
Data Index: 2374872 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4786. Min Act: -0.1700
Data Index: 270721 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4786. Min Act: -0.1700
Data Index: 8250037 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4786. Min Act: -0.1700
Data Index: 8002130 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4473. Min Act: -0.1700
Data Index: 6713903 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4473. Min Act: -0.1700
Data Index: 5882640 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4473. Min Act: -0.1700
Data Index: 3092001 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4161. Min Act: -0.1700
Data Index: 6320333 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4161. Min Act: -0.1700
Data Index: 1018907 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4161. Min Act: -0.1700
Data Index: 8706775 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.4161. Min Act: -0.1700
Data Index: 7480007 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.3848. Min Act: -0.1700
Data Index: 4764569 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.3848. Min Act: -0.1700
Data Index: 7447558 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.3848. Min Act: -0.1700
Data Index: 5203332 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5411. Min Range: -4.5411
Max Act: 4.3848. Min Act: -0.1700
Data Index: 7891959 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19