Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4355 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.1264. Min Range: -15.1264
Max Act: 15.1264. Min Act: -0.1700
Data Index: 1440605 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.1264. Min Range: -15.1264
Max Act: 15.0639. Min Act: -0.1700
Data Index: 6662109 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.9389. Min Act: -0.1700
Data Index: 7922620 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.9389. Min Act: -0.1700
Data Index: 1521390 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.8764. Min Act: -0.1700
Data Index: 8124501 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.8139. Min Act: -0.1700
Data Index: 8165619 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.8139. Min Act: -0.1700
Data Index: 3277071 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.7514. Min Act: -0.1700
Data Index: 3439589 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.6889. Min Act: -0.1700
Data Index: 7942732 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.6889. Min Act: -0.1700
Data Index: 3619962 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.6264. Min Act: -0.1700
Data Index: 218294 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.6264. Min Act: -0.1700
Data Index: 3475085 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.6264. Min Act: -0.1700
Data Index: 2811366 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.6264. Min Act: -0.1700
Data Index: 1849957 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.6264. Min Act: -0.1700
Data Index: 1447632 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.6264. Min Act: -0.1700
Data Index: 3327399 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.5639. Min Act: -0.1700
Data Index: 7251454 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.5639. Min Act: -0.1700
Data Index: 383392 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.5639. Min Act: -0.1700
Data Index: 3327020 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.1264. Min Range: -15.1264
Max Act: 14.5639. Min Act: -0.1700
Data Index: 8401561 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19