Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2890 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4727. Min Range: -8.4727
Max Act: 8.4727. Min Act: -0.1700
Data Index: 5440522 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4727. Min Range: -8.4727
Max Act: 8.2852. Min Act: -0.1700
Data Index: 3143595 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4727. Min Range: -8.4727
Max Act: 8.0352. Min Act: -0.1700
Data Index: 4514516 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.9727. Min Act: -0.1700
Data Index: 7725633 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.7852. Min Act: -0.1700
Data Index: 7095323 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.7852. Min Act: -0.1700
Data Index: 863096 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.7227. Min Act: -0.1700
Data Index: 5391075 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.7227. Min Act: -0.1700
Data Index: 7308236 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.6602. Min Act: -0.1700
Data Index: 3359464 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.6602. Min Act: -0.1700
Data Index: 3349228 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.5977. Min Act: -0.1700
Data Index: 3058678 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.5664. Min Act: -0.1700
Data Index: 4968543 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.5977. Min Act: -0.1700
Data Index: 3020080 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.5664. Min Act: -0.1700
Data Index: 8828251 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.5352. Min Act: -0.1700
Data Index: 7592079 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.5352. Min Act: -0.1700
Data Index: 7466141 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.5352. Min Act: -0.1700
Data Index: 6082463 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.5352. Min Act: -0.1700
Data Index: 2775363 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.5352. Min Act: -0.1700
Data Index: 1913236 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4727. Min Range: -8.4727
Max Act: 7.5352. Min Act: -0.1700
Data Index: 3338655 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19