Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1858 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.2366. Min Act: -0.1700
Data Index: 709221 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.2208. Min Act: -0.1700
Data Index: 1552687 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.2208. Min Act: -0.1700
Data Index: 7066558 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.1894. Min Act: -0.1700
Data Index: 6578844 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0949. Min Act: -0.1700
Data Index: 5818007 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0949. Min Act: -0.1700
Data Index: 6618816 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0792. Min Act: -0.1700
Data Index: 3011193 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0949. Min Act: -0.1700
Data Index: 6216000 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0792. Min Act: -0.1700
Data Index: 2854213 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0792. Min Act: -0.1700
Data Index: 6928047 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0634. Min Act: -0.1700
Data Index: 2885097 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0634. Min Act: -0.1700
Data Index: 7305975 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0634. Min Act: -0.1700
Data Index: 5175979 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0476. Min Act: -0.1700
Data Index: 6044765 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0476. Min Act: -0.1700
Data Index: 994861 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0318. Min Act: -0.1700
Data Index: 2176964 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0476. Min Act: -0.1700
Data Index: 4401410 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0318. Min Act: -0.1700
Data Index: 3200632 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0318. Min Act: -0.1700
Data Index: 5087326 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2366. Min Range: -3.2366
Max Act: 3.0002. Min Act: -0.1700
Data Index: 7435917 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19