Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2067 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.5132. Min Act: -0.1700
Data Index: 4535411 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.4195. Min Act: -0.1700
Data Index: 7849000 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.2319. Min Act: -0.1700
Data Index: 991923 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.2319. Min Act: -0.1700
Data Index: 5044401 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.2319. Min Act: -0.1700
Data Index: 1774041 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.2007. Min Act: -0.1700
Data Index: 8487877 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.1694. Min Act: -0.1700
Data Index: 6026963 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.1694. Min Act: -0.1700
Data Index: 2016841 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.1694. Min Act: -0.1700
Data Index: 5915309 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.1694. Min Act: -0.1700
Data Index: 4463095 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.2007. Min Act: -0.1700
Data Index: 5678860 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.1694. Min Act: -0.1700
Data Index: 4761401 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.1382. Min Act: -0.1700
Data Index: 2157245 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.1069. Min Act: -0.1700
Data Index: 3208694 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.0757. Min Act: -0.1700
Data Index: 2174748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.0444. Min Act: -0.1700
Data Index: 3903075 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.1069. Min Act: -0.1700
Data Index: 7544554 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.0757. Min Act: -0.1700
Data Index: 422440 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.0444. Min Act: -0.1700
Data Index: 3917888 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5132. Min Range: -4.5132
Max Act: 4.0444. Min Act: -0.1700
Data Index: 5420390 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19