Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.8283. Min Act: -0.1700
Data Index: 3460983 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.7033. Min Act: -0.1700
Data Index: 528502 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.6721. Min Act: -0.1699
Data Index: 5521167 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.6408. Min Act: -0.1700
Data Index: 2565540 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.6408. Min Act: -0.1700
Data Index: 4478255 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.5471. Min Act: -0.1700
Data Index: 1732017 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.5158. Min Act: -0.1700
Data Index: 7103000 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.5471. Min Act: -0.1700
Data Index: 8367076 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.5471. Min Act: -0.1700
Data Index: 7468573 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.5471. Min Act: -0.1700
Data Index: 90395 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.5783. Min Act: -0.1700
Data Index: 8106716 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.5471. Min Act: -0.1700
Data Index: 8367084 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.5158. Min Act: -0.1698
Data Index: 8367083 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.4846. Min Act: -0.1700
Data Index: 8107788 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.4846. Min Act: -0.1700
Data Index: 2592943 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.4846. Min Act: -0.1700
Data Index: 534804 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.4221. Min Act: -0.1700
Data Index: 1183645 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.4533. Min Act: -0.1700
Data Index: 6549443 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.4221. Min Act: -0.1700
Data Index: 7910759 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8283. Min Range: -5.8283
Max Act: 5.4221. Min Act: -0.1700
Data Index: 6326973 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19