Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4620 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1679. Min Range: -6.1679
Max Act: 6.1679. Min Act: -0.1700
Data Index: 5146352 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1679. Min Range: -6.1679
Max Act: 6.1366. Min Act: -0.1700
Data Index: 5120232 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1679. Min Range: -6.1679
Max Act: 6.1366. Min Act: -0.1700
Data Index: 5506626 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1679. Min Range: -6.1679
Max Act: 6.0429. Min Act: -0.1700
Data Index: 8593643 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1679. Min Range: -6.1679
Max Act: 6.0429. Min Act: -0.1700
Data Index: 3166330 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.9491. Min Act: -0.1700
Data Index: 5669195 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.8866. Min Act: -0.1700
Data Index: 5406332 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.9179. Min Act: -0.1700
Data Index: 2648349 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.8554. Min Act: -0.1700
Data Index: 6999615 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.8554. Min Act: -0.1700
Data Index: 6296682 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.8554. Min Act: -0.1700
Data Index: 5268966 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.8554. Min Act: -0.1700
Data Index: 1106588 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.8241. Min Act: -0.1700
Data Index: 2760415 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.8241. Min Act: -0.1700
Data Index: 4255605 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.7929. Min Act: -0.1700
Data Index: 1801460 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.8241. Min Act: -0.1700
Data Index: 8688398 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.8241. Min Act: -0.1700
Data Index: 6069571 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.8241. Min Act: -0.1700
Data Index: 443350 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.7929. Min Act: -0.1700
Data Index: 3622717 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1679. Min Range: -6.1679
Max Act: 5.7616. Min Act: -0.1700
Data Index: 4986368 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19