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

Dataset: Open Web Text

Neuron 1821 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: 4.9238. Min Range: -4.9238

Max Act: 4.9238. Min Act: -0.1700

Data Index: 2818727 (Open Web Text)

Max Activating Token Index: 923

Text #1

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.9149. Min Act: -0.1700

Data Index: 6032750 (Open Web Text)

Max Activating Token Index: 446

Text #2

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.8864. Min Act: -0.1700

Data Index: 3246436 (Open Web Text)

Max Activating Token Index: 481

Text #3

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.8901. Min Act: -0.1700

Data Index: 5942037 (Open Web Text)

Max Activating Token Index: 443

Text #4

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.8533. Min Act: -0.1700

Data Index: 2996800 (Open Web Text)

Max Activating Token Index: 237

Text #5

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.8167. Min Act: -0.1700

Data Index: 4071415 (Open Web Text)

Max Activating Token Index: 552

Text #6

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.8329. Min Act: -0.1700

Data Index: 2679496 (Open Web Text)

Max Activating Token Index: 982

Text #7

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.8252. Min Act: -0.1700

Data Index: 5677408 (Open Web Text)

Max Activating Token Index: 857

Text #8

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.7926. Min Act: -0.1700

Data Index: 1582349 (Open Web Text)

Max Activating Token Index: 544

Text #9

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.7872. Min Act: -0.1700

Data Index: 171224 (Open Web Text)

Max Activating Token Index: 374

Text #10

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.7587. Min Act: -0.1700

Data Index: 3147834 (Open Web Text)

Max Activating Token Index: 696

Text #11

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.7697. Min Act: -0.1700

Data Index: 7722761 (Open Web Text)

Max Activating Token Index: 931

Text #12

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.7906. Min Act: -0.1700

Data Index: 5177073 (Open Web Text)

Max Activating Token Index: 915

Text #13

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.7391. Min Act: -0.1700

Data Index: 6547985 (Open Web Text)

Max Activating Token Index: 689

Text #14

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.7343. Min Act: -0.1700

Data Index: 5412012 (Open Web Text)

Max Activating Token Index: 255

Text #15

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.7579. Min Act: -0.1700

Data Index: 7933007 (Open Web Text)

Max Activating Token Index: 387

Text #16

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.7471. Min Act: -0.1700

Data Index: 1585946 (Open Web Text)

Max Activating Token Index: 960

Text #17

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.7444. Min Act: -0.1700

Data Index: 2461725 (Open Web Text)

Max Activating Token Index: 524

Text #18

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.7016. Min Act: -0.1700

Data Index: 3485755 (Open Web Text)

Max Activating Token Index: 735

Text #19

Max Range: 4.9238. Min Range: -4.9238

Max Act: 4.7178. Min Act: -0.1700

Data Index: 3735396 (Open Web Text)

Max Activating Token Index: 758