Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1009 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6264. Min Range: -6.6264
Max Act: 6.6264. Min Act: -0.1700
Data Index: 4572415 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6264. Min Range: -6.6264
Max Act: 6.5952. Min Act: -0.1700
Data Index: 1536593 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6264. Min Range: -6.6264
Max Act: 6.2202. Min Act: -0.1700
Data Index: 7515540 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6264. Min Range: -6.6264
Max Act: 6.1264. Min Act: -0.1700
Data Index: 4409646 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6264. Min Range: -6.6264
Max Act: 6.0952. Min Act: -0.1700
Data Index: 153488 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6264. Min Range: -6.6264
Max Act: 6.0639. Min Act: -0.1700
Data Index: 1022987 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6264. Min Range: -6.6264
Max Act: 6.0014. Min Act: -0.1700
Data Index: 2074036 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6264. Min Range: -6.6264
Max Act: 6.0639. Min Act: -0.1700
Data Index: 3296328 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6264. Min Range: -6.6264
Max Act: 5.9702. Min Act: -0.1700
Data Index: 4343191 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6264. Min Range: -6.6264
Max Act: 5.9702. Min Act: -0.1700
Data Index: 863754 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6264. Min Range: -6.6264
Max Act: 5.9389. Min Act: -0.1700
Data Index: 5280723 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6264. Min Range: -6.6264
Max Act: 5.9389. Min Act: -0.1700
Data Index: 5729362 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6264. Min Range: -6.6264
Max Act: 5.8452. Min Act: -0.1700
Data Index: 3682383 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6264. Min Range: -6.6264
Max Act: 5.8764. Min Act: -0.1700
Data Index: 7631289 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6264. Min Range: -6.6264
Max Act: 5.8452. Min Act: -0.1700
Data Index: 6340886 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6264. Min Range: -6.6264
Max Act: 5.8452. Min Act: -0.1700
Data Index: 5523269 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6264. Min Range: -6.6264
Max Act: 5.9077. Min Act: -0.1700
Data Index: 4110228 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6264. Min Range: -6.6264
Max Act: 5.8139. Min Act: -0.1700
Data Index: 4612633 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6264. Min Range: -6.6264
Max Act: 5.8452. Min Act: -0.1700
Data Index: 6820597 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6264. Min Range: -6.6264
Max Act: 5.8139. Min Act: -0.1700
Data Index: 3442729 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19