Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 640 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.7070. Min Act: -0.1700

Data Index: 5359862 (Open Web Text)

Max Activating Token Index: 223

Text #1

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.7158. Min Act: -0.1700

Data Index: 5644366 (Open Web Text)

Max Activating Token Index: 603

Text #2

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.7364. Min Act: -0.1700

Data Index: 2894038 (Open Web Text)

Max Activating Token Index: 686

Text #3

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.7138. Min Act: -0.1700

Data Index: 4299475 (Open Web Text)

Max Activating Token Index: 392

Text #4

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.7186. Min Act: -0.1700

Data Index: 3605290 (Open Web Text)

Max Activating Token Index: 450

Text #5

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.6859. Min Act: -0.1700

Data Index: 6553382 (Open Web Text)

Max Activating Token Index: 130

Text #6

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.6575. Min Act: -0.1700

Data Index: 5966912 (Open Web Text)

Max Activating Token Index: 83

Text #7

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.6397. Min Act: -0.1700

Data Index: 4045134 (Open Web Text)

Max Activating Token Index: 777

Text #8

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.6500. Min Act: -0.1700

Data Index: 2991263 (Open Web Text)

Max Activating Token Index: 461

Text #9

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.6271. Min Act: -0.1700

Data Index: 3285757 (Open Web Text)

Max Activating Token Index: 637

Text #10

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.6264. Min Act: -0.1700

Data Index: 8515411 (Open Web Text)

Max Activating Token Index: 272

Text #11

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.5912. Min Act: -0.1700

Data Index: 2420748 (Open Web Text)

Max Activating Token Index: 584

Text #12

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.5947. Min Act: -0.1700

Data Index: 7055984 (Open Web Text)

Max Activating Token Index: 983

Text #13

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.5914. Min Act: -0.1700

Data Index: 5966909 (Open Web Text)

Max Activating Token Index: 423

Text #14

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.5908. Min Act: -0.1700

Data Index: 2787235 (Open Web Text)

Max Activating Token Index: 1017

Text #15

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.5931. Min Act: -0.1700

Data Index: 4904931 (Open Web Text)

Max Activating Token Index: 100

Text #16

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.5853. Min Act: -0.1700

Data Index: 4669024 (Open Web Text)

Max Activating Token Index: 436

Text #17

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.5434. Min Act: -0.1700

Data Index: 2420749 (Open Web Text)

Max Activating Token Index: 319

Text #18

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.5644. Min Act: -0.1700

Data Index: 4722973 (Open Web Text)

Max Activating Token Index: 1009

Text #19

Max Range: 4.7364. Min Range: -4.7364

Max Act: 4.5464. Min Act: -0.1700

Data Index: 3300943 (Open Web Text)

Max Activating Token Index: 385