Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.7777. Min Act: -0.1700
Data Index: 6828473 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.7152. Min Act: -0.1700
Data Index: 7054826 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.6527. Min Act: -0.1700
Data Index: 5223257 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.6527. Min Act: -0.1700
Data Index: 117627 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.6214. Min Act: -0.1700
Data Index: 1468224 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.5902. Min Act: -0.1700
Data Index: 4430945 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.5589. Min Act: -0.1700
Data Index: 696812 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.5277. Min Act: -0.1700
Data Index: 4147466 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.5277. Min Act: -0.1700
Data Index: 4993261 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.4964. Min Act: -0.1700
Data Index: 6381007 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.4964. Min Act: -0.1700
Data Index: 2781336 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.4652. Min Act: -0.1700
Data Index: 3074314 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.4652. Min Act: -0.1700
Data Index: 4399039 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.4339. Min Act: -0.1700
Data Index: 5576376 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.4339. Min Act: -0.1700
Data Index: 4996327 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.4339. Min Act: -0.1700
Data Index: 6304704 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.4027. Min Act: -0.1700
Data Index: 5791649 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.4027. Min Act: -0.1700
Data Index: 6451041 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.3714. Min Act: -0.1700
Data Index: 5361715 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7777. Min Range: -5.7777
Max Act: 5.3714. Min Act: -0.1700
Data Index: 236009 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19