Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 88 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.8431. Min Range: -9.8431
Max Act: 9.8431. Min Act: -0.1700
Data Index: 8460860 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8431. Min Range: -9.8431
Max Act: 9.2181. Min Act: -0.1700
Data Index: 2519494 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8431. Min Range: -9.8431
Max Act: 9.2181. Min Act: -0.1700
Data Index: 5506606 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8431. Min Range: -9.8431
Max Act: 9.2181. Min Act: -0.1700
Data Index: 4868993 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8431. Min Range: -9.8431
Max Act: 9.2181. Min Act: -0.1700
Data Index: 4891717 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8431. Min Range: -9.8431
Max Act: 9.0931. Min Act: -0.1700
Data Index: 6808368 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8431. Min Range: -9.8431
Max Act: 9.0931. Min Act: -0.1700
Data Index: 1063159 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8431. Min Range: -9.8431
Max Act: 9.0306. Min Act: -0.1700
Data Index: 4637001 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8431. Min Range: -9.8431
Max Act: 9.0306. Min Act: -0.1700
Data Index: 8122814 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8431. Min Range: -9.8431
Max Act: 8.9681. Min Act: -0.1700
Data Index: 8348566 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8431. Min Range: -9.8431
Max Act: 8.9681. Min Act: -0.1698
Data Index: 7091844 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8431. Min Range: -9.8431
Max Act: 8.8431. Min Act: -0.1700
Data Index: 2275264 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8431. Min Range: -9.8431
Max Act: 8.9056. Min Act: -0.1700
Data Index: 2506461 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8431. Min Range: -9.8431
Max Act: 8.9056. Min Act: -0.1700
Data Index: 2453129 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8431. Min Range: -9.8431
Max Act: 8.9056. Min Act: -0.1700
Data Index: 556235 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8431. Min Range: -9.8431
Max Act: 8.7806. Min Act: -0.1700
Data Index: 7193091 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8431. Min Range: -9.8431
Max Act: 8.8431. Min Act: -0.1700
Data Index: 4609749 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8431. Min Range: -9.8431
Max Act: 8.8431. Min Act: -0.1700
Data Index: 7795473 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8431. Min Range: -9.8431
Max Act: 8.8431. Min Act: -0.1700
Data Index: 2496474 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8431. Min Range: -9.8431
Max Act: 8.8431. Min Act: -0.1700
Data Index: 6406678 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19