Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2891 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1296. Min Range: -6.1296
Max Act: 6.1296. Min Act: -0.1700
Data Index: 787064 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1296. Min Range: -6.1296
Max Act: 6.0983. Min Act: -0.1700
Data Index: 5082880 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.9733. Min Act: -0.1700
Data Index: 4879353 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.9733. Min Act: -0.1700
Data Index: 1258065 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.7546. Min Act: -0.1700
Data Index: 517729 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.7546. Min Act: -0.1700
Data Index: 6210198 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.7546. Min Act: -0.1700
Data Index: 6243286 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.7233. Min Act: -0.1700
Data Index: 613285 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.7546. Min Act: -0.1700
Data Index: 1855386 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.6608. Min Act: -0.1700
Data Index: 35001 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.6921. Min Act: -0.1700
Data Index: 6972958 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.6608. Min Act: -0.1700
Data Index: 4591908 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.6921. Min Act: -0.1700
Data Index: 8786291 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.6608. Min Act: -0.1700
Data Index: 2668247 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.6608. Min Act: -0.1700
Data Index: 3466950 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.6608. Min Act: -0.1700
Data Index: 4159401 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.6296. Min Act: -0.1700
Data Index: 2881647 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.6296. Min Act: -0.1700
Data Index: 3528610 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.6296. Min Act: -0.1700
Data Index: 7066362 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1296. Min Range: -6.1296
Max Act: 5.6296. Min Act: -0.1700
Data Index: 8262646 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19