Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.9385. Min Act: -0.1700
Data Index: 1880612 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.8135. Min Act: -0.1700
Data Index: 2158786 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.7822. Min Act: -0.1700
Data Index: 6383668 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.6885. Min Act: -0.1700
Data Index: 7771289 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.6260. Min Act: -0.1700
Data Index: 3462422 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.6260. Min Act: -0.1700
Data Index: 1643602 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5947. Min Act: -0.1700
Data Index: 6921633 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5947. Min Act: -0.1700
Data Index: 7828519 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.6260. Min Act: -0.1700
Data Index: 3683003 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5322. Min Act: -0.1700
Data Index: 5671244 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5635. Min Act: -0.1700
Data Index: 4576967 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5635. Min Act: -0.1700
Data Index: 2346263 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5635. Min Act: -0.1700
Data Index: 1312410 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5635. Min Act: -0.1700
Data Index: 6435613 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5947. Min Act: -0.1700
Data Index: 524401 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5635. Min Act: -0.1700
Data Index: 5005499 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5322. Min Act: -0.1700
Data Index: 4184699 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5010. Min Act: -0.1700
Data Index: 1675931 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5010. Min Act: -0.1700
Data Index: 5198186 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9385. Min Range: -5.9385
Max Act: 5.5010. Min Act: -0.1700
Data Index: 5851907 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19