Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4452 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8487. Min Range: -8.8487
Max Act: 8.8487. Min Act: -0.1700
Data Index: 6968339 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8487. Min Range: -8.8487
Max Act: 8.3487. Min Act: -0.1700
Data Index: 6260963 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8487. Min Range: -8.8487
Max Act: 8.2237. Min Act: -0.1700
Data Index: 3775543 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8487. Min Range: -8.8487
Max Act: 8.1612. Min Act: -0.1700
Data Index: 7151262 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8487. Min Range: -8.8487
Max Act: 8.1612. Min Act: -0.1700
Data Index: 7940838 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.9737. Min Act: -0.1700
Data Index: 3201657 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8487. Min Range: -8.8487
Max Act: 8.0362. Min Act: -0.1700
Data Index: 7272574 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.9737. Min Act: -0.1700
Data Index: 4140729 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.9112. Min Act: -0.1700
Data Index: 2755536 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.9737. Min Act: -0.1700
Data Index: 8079130 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.9112. Min Act: -0.1700
Data Index: 6865306 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.9112. Min Act: -0.1700
Data Index: 2096707 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.8487. Min Act: -0.1700
Data Index: 5840204 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.8487. Min Act: -0.1700
Data Index: 1169192 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.7862. Min Act: -0.1700
Data Index: 364009 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.8487. Min Act: -0.1700
Data Index: 3781962 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.7862. Min Act: -0.1700
Data Index: 2811031 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.7862. Min Act: -0.1700
Data Index: 542337 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.7862. Min Act: -0.1700
Data Index: 1812272 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8487. Min Range: -8.8487
Max Act: 7.7862. Min Act: -0.1700
Data Index: 6036989 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19