Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3954 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3795. Min Range: -8.3795
Max Act: 8.3795. Min Act: -0.1700
Data Index: 2329611 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3795. Min Range: -8.3795
Max Act: 8.3483. Min Act: -0.1700
Data Index: 7457083 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3795. Min Range: -8.3795
Max Act: 8.2233. Min Act: -0.1700
Data Index: 6320466 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3795. Min Range: -8.3795
Max Act: 8.0358. Min Act: -0.1700
Data Index: 6286321 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.9733. Min Act: -0.1700
Data Index: 1018975 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.8170. Min Act: -0.1700
Data Index: 962339 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.7545. Min Act: -0.1700
Data Index: 5751137 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.7545. Min Act: -0.1700
Data Index: 5012089 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.7545. Min Act: -0.1700
Data Index: 3799932 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.7233. Min Act: -0.1700
Data Index: 3235697 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.7233. Min Act: -0.1700
Data Index: 5164724 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.6608. Min Act: -0.1700
Data Index: 3668906 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.6920. Min Act: -0.1700
Data Index: 7620257 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.6920. Min Act: -0.1700
Data Index: 4935179 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.6608. Min Act: -0.1700
Data Index: 2848158 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.6608. Min Act: -0.1700
Data Index: 6163786 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.6608. Min Act: -0.1700
Data Index: 7215222 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.6295. Min Act: -0.1700
Data Index: 826664 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.5983. Min Act: -0.1700
Data Index: 8335746 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3795. Min Range: -8.3795
Max Act: 7.6295. Min Act: -0.1700
Data Index: 402585 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19