Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3965 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0274. Min Range: -7.0274
Max Act: 7.0274. Min Act: -0.1700
Data Index: 7964473 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.7149. Min Act: -0.1700
Data Index: 2913338 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.4962. Min Act: -0.1700
Data Index: 330417 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.4649. Min Act: -0.1700
Data Index: 8121280 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.4337. Min Act: -0.1700
Data Index: 1469802 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.4337. Min Act: -0.1700
Data Index: 3871359 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.4337. Min Act: -0.1700
Data Index: 2370011 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.4337. Min Act: -0.1700
Data Index: 5555950 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.4024. Min Act: -0.1700
Data Index: 1658536 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.4024. Min Act: -0.1700
Data Index: 196688 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.3712. Min Act: -0.1700
Data Index: 2691191 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.3712. Min Act: -0.1700
Data Index: 8486098 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.3399. Min Act: -0.1700
Data Index: 8740787 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.3087. Min Act: -0.1700
Data Index: 1913447 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.3087. Min Act: -0.1700
Data Index: 5686336 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.3399. Min Act: -0.1700
Data Index: 5575800 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.3087. Min Act: -0.1700
Data Index: 3833516 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.2462. Min Act: -0.1700
Data Index: 3833517 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.2462. Min Act: -0.1700
Data Index: 2566540 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0274. Min Range: -7.0274
Max Act: 6.1837. Min Act: -0.1700
Data Index: 5112360 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19