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

Dataset: Open Web Text

Neuron 332 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: 5.3090. Min Range: -5.3090

Max Act: 5.3090. Min Act: -0.1700

Data Index: 2165142 (Open Web Text)

Max Activating Token Index: 978

Text #1

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.2243. Min Act: -0.1700

Data Index: 4080816 (Open Web Text)

Max Activating Token Index: 781

Text #2

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.1189. Min Act: -0.1700

Data Index: 722658 (Open Web Text)

Max Activating Token Index: 390

Text #3

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.1066. Min Act: -0.1700

Data Index: 3147794 (Open Web Text)

Max Activating Token Index: 927

Text #4

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0778. Min Act: -0.1700

Data Index: 921958 (Open Web Text)

Max Activating Token Index: 359

Text #5

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0403. Min Act: -0.1700

Data Index: 3650040 (Open Web Text)

Max Activating Token Index: 357

Text #6

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0306. Min Act: -0.1700

Data Index: 4728897 (Open Web Text)

Max Activating Token Index: 130

Text #7

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0463. Min Act: -0.1700

Data Index: 4517109 (Open Web Text)

Max Activating Token Index: 436

Text #8

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0567. Min Act: -0.1700

Data Index: 3189921 (Open Web Text)

Max Activating Token Index: 292

Text #9

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.9802. Min Act: -0.1700

Data Index: 1056603 (Open Web Text)

Max Activating Token Index: 147

Text #10

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.9853. Min Act: -0.1700

Data Index: 7539469 (Open Web Text)

Max Activating Token Index: 952

Text #11

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.9610. Min Act: -0.1700

Data Index: 2609347 (Open Web Text)

Max Activating Token Index: 98

Text #12

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.9654. Min Act: -0.1700

Data Index: 8136024 (Open Web Text)

Max Activating Token Index: 943

Text #13

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.9281. Min Act: -0.1700

Data Index: 4026950 (Open Web Text)

Max Activating Token Index: 478

Text #14

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.9189. Min Act: -0.1700

Data Index: 8373098 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.9233. Min Act: -0.1700

Data Index: 4840100 (Open Web Text)

Max Activating Token Index: 509

Text #16

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.9299. Min Act: -0.1700

Data Index: 5411200 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.9276. Min Act: -0.1700

Data Index: 1349101 (Open Web Text)

Max Activating Token Index: 672

Text #18

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.8916. Min Act: -0.1700

Data Index: 3579266 (Open Web Text)

Max Activating Token Index: 406

Text #19

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.8979. Min Act: -0.1700

Data Index: 4606637 (Open Web Text)

Max Activating Token Index: 301