Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2031 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.7927. Min Act: -0.1700
Data Index: 303095 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.4177. Min Act: -0.1700
Data Index: 450644 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.4177. Min Act: -0.1700
Data Index: 450648 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.4177. Min Act: -0.1700
Data Index: 1423436 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.3240. Min Act: -0.1700
Data Index: 1229590 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.2614. Min Act: -0.1700
Data Index: 4504599 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.1989. Min Act: -0.1700
Data Index: 6493182 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.1677. Min Act: -0.1700
Data Index: 1589211 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.1677. Min Act: -0.1700
Data Index: 1278130 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.1364. Min Act: -0.1700
Data Index: 6164484 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.1052. Min Act: -0.1700
Data Index: 6380276 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.0739. Min Act: -0.1700
Data Index: 6535304 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.0427. Min Act: -0.1700
Data Index: 577662 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.0427. Min Act: -0.1700
Data Index: 3377451 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.0427. Min Act: -0.1700
Data Index: 2586148 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.0427. Min Act: -0.1700
Data Index: 8240721 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.0114. Min Act: -0.1700
Data Index: 4926896 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.0114. Min Act: -0.1700
Data Index: 6428328 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.0114. Min Act: -0.1700
Data Index: 7143805 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.0114. Min Act: -0.1700
Data Index: 6659091 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19