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

Dataset: Open Web Text

Neuron 15 in Layer 24

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8320. Min Act: -0.1700

Data Index: 7973235 (Open Web Text)

Max Activating Token Index: 943

Text #1

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7382. Min Act: -0.1700

Data Index: 2048654 (Open Web Text)

Max Activating Token Index: 404

Text #2

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7382. Min Act: -0.1700

Data Index: 2872167 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6757. Min Act: -0.1700

Data Index: 5218110 (Open Web Text)

Max Activating Token Index: 486

Text #4

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6757. Min Act: -0.1700

Data Index: 449298 (Open Web Text)

Max Activating Token Index: 381

Text #5

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6132. Min Act: -0.1700

Data Index: 1736662 (Open Web Text)

Max Activating Token Index: 623

Text #6

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6132. Min Act: -0.1700

Data Index: 2011057 (Open Web Text)

Max Activating Token Index: 515

Text #7

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6132. Min Act: -0.1700

Data Index: 1830682 (Open Web Text)

Max Activating Token Index: 523

Text #8

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5820. Min Act: -0.1700

Data Index: 4160663 (Open Web Text)

Max Activating Token Index: 962

Text #9

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5507. Min Act: -0.1700

Data Index: 6157217 (Open Web Text)

Max Activating Token Index: 355

Text #10

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5507. Min Act: -0.1700

Data Index: 6960095 (Open Web Text)

Max Activating Token Index: 678

Text #11

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5507. Min Act: -0.1700

Data Index: 487318 (Open Web Text)

Max Activating Token Index: 403

Text #12

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5507. Min Act: -0.1700

Data Index: 307268 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 4274690 (Open Web Text)

Max Activating Token Index: 342

Text #14

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 2208507 (Open Web Text)

Max Activating Token Index: 548

Text #15

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 6601443 (Open Web Text)

Max Activating Token Index: 332

Text #16

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 4832969 (Open Web Text)

Max Activating Token Index: 347

Text #17

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 3558168 (Open Web Text)

Max Activating Token Index: 292

Text #18

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4882. Min Act: -0.1700

Data Index: 2856867 (Open Web Text)

Max Activating Token Index: 57

Text #19

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4882. Min Act: -0.1700

Data Index: 2981440 (Open Web Text)

Max Activating Token Index: 711