Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.6835. Min Act: -0.1700
Data Index: 7690801 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.6835. Min Act: -0.1700
Data Index: 6744466 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.6835. Min Act: -0.1700
Data Index: 8137378 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.6210. Min Act: -0.1700
Data Index: 2773365 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.5585. Min Act: -0.1700
Data Index: 3739606 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.5273. Min Act: -0.1700
Data Index: 1491992 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.5273. Min Act: -0.1700
Data Index: 8350698 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.5273. Min Act: -0.1700
Data Index: 5464190 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.4648. Min Act: -0.1700
Data Index: 3625346 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.4648. Min Act: -0.1700
Data Index: 6896672 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.4960. Min Act: -0.1700
Data Index: 2164603 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.4960. Min Act: -0.1700
Data Index: 6984860 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.4648. Min Act: -0.1700
Data Index: 7595960 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.4335. Min Act: -0.1700
Data Index: 1731988 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.4023. Min Act: -0.1700
Data Index: 4011593 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.4023. Min Act: -0.1700
Data Index: 4763824 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.3710. Min Act: -0.1700
Data Index: 8137377 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.3398. Min Act: -0.1700
Data Index: 7183158 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.3710. Min Act: -0.1700
Data Index: 7858379 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6835. Min Range: -5.6835
Max Act: 5.3710. Min Act: -0.1700
Data Index: 1953008 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19