Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 3030 in Layer 44

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 8.8080. Min Range: -8.8080

Max Act: 8.8080. Min Act: -0.1700

Data Index: 1388427 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 8.8080. Min Range: -8.8080

Max Act: 8.4330. Min Act: -0.1700

Data Index: 4751717 (Open Web Text)

Max Activating Token Index: 307

Text #2

Max Range: 8.8080. Min Range: -8.8080

Max Act: 8.3705. Min Act: -0.1700

Data Index: 1808832 (Open Web Text)

Max Activating Token Index: 362

Text #3

Max Range: 8.8080. Min Range: -8.8080

Max Act: 8.3705. Min Act: -0.1700

Data Index: 6127920 (Open Web Text)

Max Activating Token Index: 713

Text #4

Max Range: 8.8080. Min Range: -8.8080

Max Act: 8.3080. Min Act: -0.1700

Data Index: 1019509 (Open Web Text)

Max Activating Token Index: 398

Text #5

Max Range: 8.8080. Min Range: -8.8080

Max Act: 8.2455. Min Act: -0.1700

Data Index: 3635286 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 8.8080. Min Range: -8.8080

Max Act: 8.0580. Min Act: -0.1700

Data Index: 5614664 (Open Web Text)

Max Activating Token Index: 855

Text #7

Max Range: 8.8080. Min Range: -8.8080

Max Act: 8.0580. Min Act: -0.1700

Data Index: 1583315 (Open Web Text)

Max Activating Token Index: 406

Text #8

Max Range: 8.8080. Min Range: -8.8080

Max Act: 7.9955. Min Act: -0.1700

Data Index: 3152453 (Open Web Text)

Max Activating Token Index: 559

Text #9

Max Range: 8.8080. Min Range: -8.8080

Max Act: 7.9018. Min Act: -0.1700

Data Index: 5836913 (Open Web Text)

Max Activating Token Index: 392

Text #10

Max Range: 8.8080. Min Range: -8.8080

Max Act: 7.9018. Min Act: -0.1700

Data Index: 7738737 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 8.8080. Min Range: -8.8080

Max Act: 7.9643. Min Act: -0.1700

Data Index: 7891436 (Open Web Text)

Max Activating Token Index: 602

Text #12

Max Range: 8.8080. Min Range: -8.8080

Max Act: 7.8705. Min Act: -0.1700

Data Index: 7959113 (Open Web Text)

Max Activating Token Index: 82

Text #13

Max Range: 8.8080. Min Range: -8.8080

Max Act: 7.8705. Min Act: -0.1700

Data Index: 3448412 (Open Web Text)

Max Activating Token Index: 675

Text #14

Max Range: 8.8080. Min Range: -8.8080

Max Act: 7.8393. Min Act: -0.1700

Data Index: 5863598 (Open Web Text)

Max Activating Token Index: 794

Text #15

Max Range: 8.8080. Min Range: -8.8080

Max Act: 7.8080. Min Act: -0.1700

Data Index: 3090521 (Open Web Text)

Max Activating Token Index: 65

Text #16

Max Range: 8.8080. Min Range: -8.8080

Max Act: 7.8080. Min Act: -0.1700

Data Index: 7063679 (Open Web Text)

Max Activating Token Index: 413

Text #17

Max Range: 8.8080. Min Range: -8.8080

Max Act: 7.7768. Min Act: -0.1700

Data Index: 1080089 (Open Web Text)

Max Activating Token Index: 832

Text #18

Max Range: 8.8080. Min Range: -8.8080

Max Act: 7.7455. Min Act: -0.1700

Data Index: 843059 (Open Web Text)

Max Activating Token Index: 888

Text #19

Max Range: 8.8080. Min Range: -8.8080

Max Act: 7.7455. Min Act: -0.1700

Data Index: 4606443 (Open Web Text)

Max Activating Token Index: 298