Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4353 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.7016. Min Act: -0.1700
Data Index: 7448515 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.6703. Min Act: -0.1700
Data Index: 139102 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.6234. Min Act: -0.1700
Data Index: 3075097 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.4981. Min Act: -0.1700
Data Index: 8518680 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.4511. Min Act: -0.1700
Data Index: 668677 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.4198. Min Act: -0.1700
Data Index: 2130644 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.4355. Min Act: -0.1700
Data Index: 6339191 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.4041. Min Act: -0.1700
Data Index: 5500918 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.3884. Min Act: -0.1700
Data Index: 1205987 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.3884. Min Act: -0.1700
Data Index: 320159 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.3884. Min Act: -0.1700
Data Index: 1623842 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.3884. Min Act: -0.1700
Data Index: 4526583 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.3728. Min Act: -0.1700
Data Index: 8705728 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.3414. Min Act: -0.1700
Data Index: 2643644 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.3571. Min Act: -0.1700
Data Index: 522573 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.3571. Min Act: -0.1700
Data Index: 8828978 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.3571. Min Act: -0.1700
Data Index: 6822081 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.3257. Min Act: -0.1700
Data Index: 4301390 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.3414. Min Act: -0.1700
Data Index: 1241605 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7016. Min Range: -3.7016
Max Act: 3.3257. Min Act: -0.1700
Data Index: 3908184 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19