Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3149 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.9454. Min Act: -0.1700
Data Index: 8363440 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.8517. Min Act: -0.1700
Data Index: 7989171 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.8204. Min Act: -0.1700
Data Index: 5065044 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.8204. Min Act: -0.1700
Data Index: 7049506 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.8204. Min Act: -0.1700
Data Index: 328852 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.8204. Min Act: -0.1700
Data Index: 4205051 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.7892. Min Act: -0.1700
Data Index: 8008882 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.7579. Min Act: -0.1700
Data Index: 6764755 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.7579. Min Act: -0.1700
Data Index: 6801611 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.7267. Min Act: -0.1700
Data Index: 1633806 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.7267. Min Act: -0.1700
Data Index: 6657224 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.7267. Min Act: -0.1700
Data Index: 4210391 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.7267. Min Act: -0.1700
Data Index: 2346491 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.7267. Min Act: -0.1700
Data Index: 1184878 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.7267. Min Act: -0.1700
Data Index: 6764758 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.6954. Min Act: -0.1700
Data Index: 4939665 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.6954. Min Act: -0.1700
Data Index: 4931819 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.6954. Min Act: -0.1700
Data Index: 363969 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.6954. Min Act: -0.1700
Data Index: 3632384 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9454. Min Range: -4.9454
Max Act: 4.6642. Min Act: -0.1700
Data Index: 3535488 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19