Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.7689. Min Act: -0.1700
Data Index: 5354289 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.6439. Min Act: -0.1700
Data Index: 2450418 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.5501. Min Act: -0.1700
Data Index: 5481417 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.5501. Min Act: -0.1700
Data Index: 5998704 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.4876. Min Act: -0.1700
Data Index: 2182523 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.4876. Min Act: -0.1700
Data Index: 5056810 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.4564. Min Act: -0.1700
Data Index: 587651 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.4251. Min Act: -0.1700
Data Index: 1740298 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.3939. Min Act: -0.1700
Data Index: 5148022 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.3626. Min Act: -0.1700
Data Index: 3359619 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.3314. Min Act: -0.1700
Data Index: 4375168 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.3314. Min Act: -0.1700
Data Index: 87854 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.3314. Min Act: -0.1700
Data Index: 8684966 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.3314. Min Act: -0.1700
Data Index: 1988460 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.3001. Min Act: -0.1700
Data Index: 3289379 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.2689. Min Act: -0.1700
Data Index: 5862388 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.2376. Min Act: -0.1700
Data Index: 4325629 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.2064. Min Act: -0.1700
Data Index: 4040060 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.2064. Min Act: -0.1700
Data Index: 3598066 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7689. Min Range: -6.7689
Max Act: 6.1751. Min Act: -0.1700
Data Index: 6558738 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19