Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 778 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1357. Min Range: -8.1357
Max Act: 8.1357. Min Act: -0.1700
Data Index: 2010051 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.9170. Min Act: -0.1700
Data Index: 7253012 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.5420. Min Act: -0.1700
Data Index: 3677826 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.5107. Min Act: -0.1700
Data Index: 250550 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.4795. Min Act: -0.1700
Data Index: 6681522 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.4482. Min Act: -0.1700
Data Index: 1290761 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.4170. Min Act: -0.1700
Data Index: 5341741 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.3857. Min Act: -0.1700
Data Index: 7316555 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.3545. Min Act: -0.1700
Data Index: 8010256 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.3545. Min Act: -0.1700
Data Index: 5314498 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.3232. Min Act: -0.1700
Data Index: 2812607 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.3232. Min Act: -0.1700
Data Index: 5197192 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.2920. Min Act: -0.1700
Data Index: 384047 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.2920. Min Act: -0.1700
Data Index: 4160955 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.2607. Min Act: -0.1700
Data Index: 8585237 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.2607. Min Act: -0.1700
Data Index: 226744 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.2607. Min Act: -0.1700
Data Index: 5035664 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.2295. Min Act: -0.1700
Data Index: 5813249 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.1982. Min Act: -0.1700
Data Index: 3362561 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1357. Min Range: -8.1357
Max Act: 7.1670. Min Act: -0.1700
Data Index: 16486 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19