Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1294 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1190. Min Range: -7.1190
Max Act: 7.1190. Min Act: -0.1700
Data Index: 8349789 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.7753. Min Act: -0.1700
Data Index: 2062896 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.7128. Min Act: -0.1700
Data Index: 2195783 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.6503. Min Act: -0.1700
Data Index: 3555384 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.5565. Min Act: -0.1700
Data Index: 5691885 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.5253. Min Act: -0.1700
Data Index: 8365550 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.4940. Min Act: -0.1700
Data Index: 2021094 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.4940. Min Act: -0.1700
Data Index: 812710 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.4315. Min Act: -0.1700
Data Index: 4497929 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.3690. Min Act: -0.1700
Data Index: 4583657 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.3690. Min Act: -0.1700
Data Index: 2003681 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.3690. Min Act: -0.1700
Data Index: 4591645 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.3378. Min Act: -0.1700
Data Index: 1291950 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.3378. Min Act: -0.1700
Data Index: 487678 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.3690. Min Act: -0.1700
Data Index: 1346720 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.3065. Min Act: -0.1700
Data Index: 1708191 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.3065. Min Act: -0.1700
Data Index: 59052 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.3065. Min Act: -0.1700
Data Index: 2411295 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.3065. Min Act: -0.1700
Data Index: 2437711 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1190. Min Range: -7.1190
Max Act: 6.2753. Min Act: -0.1700
Data Index: 5943847 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19