Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5246. Min Range: -7.5246
Max Act: 7.5246. Min Act: -0.1700
Data Index: 851799 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.9309. Min Act: -0.1700
Data Index: 1012429 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.8684. Min Act: -0.1700
Data Index: 3769660 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.8059. Min Act: -0.1700
Data Index: 3099305 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.7746. Min Act: -0.1700
Data Index: 1286985 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.7746. Min Act: -0.1700
Data Index: 1200620 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.7434. Min Act: -0.1700
Data Index: 588813 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.7434. Min Act: -0.1700
Data Index: 7566307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.7434. Min Act: -0.1700
Data Index: 3777997 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.7434. Min Act: -0.1700
Data Index: 6820135 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.7121. Min Act: -0.1700
Data Index: 4427304 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.6809. Min Act: -0.1700
Data Index: 1908454 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.6496. Min Act: -0.1700
Data Index: 7336825 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.6496. Min Act: -0.1700
Data Index: 3979955 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.6496. Min Act: -0.1700
Data Index: 5663889 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.6496. Min Act: -0.1700
Data Index: 5753775 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.6184. Min Act: -0.1700
Data Index: 244115 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.5871. Min Act: -0.1700
Data Index: 4012834 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.5871. Min Act: -0.1700
Data Index: 1387449 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5246. Min Range: -7.5246
Max Act: 6.5559. Min Act: -0.1700
Data Index: 392042 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19