Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3770 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.3378. Min Act: -0.1700
Data Index: 7306623 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.3378. Min Act: -0.1700
Data Index: 1673634 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.2753. Min Act: -0.1700
Data Index: 7406539 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.2128. Min Act: -0.1700
Data Index: 3620812 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.2128. Min Act: -0.1700
Data Index: 6271000 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.1503. Min Act: -0.1700
Data Index: 5928743 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.1190. Min Act: -0.1700
Data Index: 2480385 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.1190. Min Act: -0.1700
Data Index: 6381592 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.1503. Min Act: -0.1700
Data Index: 871886 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.0878. Min Act: -0.1700
Data Index: 8213186 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.0878. Min Act: -0.1700
Data Index: 6472633 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.0878. Min Act: -0.1700
Data Index: 5869269 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.0878. Min Act: -0.1700
Data Index: 8665630 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.0565. Min Act: -0.1700
Data Index: 6268641 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.0565. Min Act: -0.1700
Data Index: 4258529 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.0565. Min Act: -0.1700
Data Index: 8739680 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.0565. Min Act: -0.1700
Data Index: 1293326 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.0253. Min Act: -0.1700
Data Index: 3841070 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3378. Min Range: -6.3378
Max Act: 5.9940. Min Act: -0.1700
Data Index: 871889 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3378. Min Range: -6.3378
Max Act: 6.0565. Min Act: -0.1700
Data Index: 7965383 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19