Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.7924. Min Act: -0.1700
Data Index: 6305864 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.7611. Min Act: -0.1700
Data Index: 8533387 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.6674. Min Act: -0.1700
Data Index: 5246825 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.6674. Min Act: -0.1700
Data Index: 4456895 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.6049. Min Act: -0.1700
Data Index: 1440114 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.5736. Min Act: -0.1700
Data Index: 529024 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.5111. Min Act: -0.1700
Data Index: 3864203 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.4799. Min Act: -0.1700
Data Index: 7829975 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.4486. Min Act: -0.1700
Data Index: 4680252 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.3861. Min Act: -0.1700
Data Index: 7361464 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.4174. Min Act: -0.1700
Data Index: 6961710 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.3861. Min Act: -0.1700
Data Index: 2469721 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.3861. Min Act: -0.1700
Data Index: 3129108 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.3549. Min Act: -0.1700
Data Index: 6931266 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.3236. Min Act: -0.1700
Data Index: 1249018 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.3236. Min Act: -0.1700
Data Index: 3504639 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.2924. Min Act: -0.1700
Data Index: 5407776 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.2924. Min Act: -0.1700
Data Index: 2363820 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.2299. Min Act: -0.1700
Data Index: 4097950 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7924. Min Range: -6.7924
Max Act: 6.2299. Min Act: -0.1700
Data Index: 339994 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19