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

Dataset: Open Web Text

Neuron 2407 in Layer 2

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: 1.9259. Min Range: -1.9259

Max Act: 1.9259. Min Act: -0.1700

Data Index: 5812257 (Open Web Text)

Max Activating Token Index: 345

Text #1

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8991. Min Act: -0.1700

Data Index: 7032430 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8926. Min Act: -0.1699

Data Index: 1717043 (Open Web Text)

Max Activating Token Index: 210

Text #3

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8950. Min Act: -0.1700

Data Index: 7032429 (Open Web Text)

Max Activating Token Index: 889

Text #4

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8641. Min Act: -0.1700

Data Index: 1010574 (Open Web Text)

Max Activating Token Index: 788

Text #5

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8406. Min Act: -0.1700

Data Index: 2064482 (Open Web Text)

Max Activating Token Index: 750

Text #6

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8364. Min Act: -0.1700

Data Index: 8110573 (Open Web Text)

Max Activating Token Index: 320

Text #7

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8317. Min Act: -0.1700

Data Index: 7439209 (Open Web Text)

Max Activating Token Index: 630

Text #8

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8304. Min Act: -0.1700

Data Index: 347524 (Open Web Text)

Max Activating Token Index: 818

Text #9

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8241. Min Act: -0.1696

Data Index: 2971127 (Open Web Text)

Max Activating Token Index: 868

Text #10

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8299. Min Act: -0.1700

Data Index: 3578000 (Open Web Text)

Max Activating Token Index: 711

Text #11

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8375. Min Act: -0.1699

Data Index: 846660 (Open Web Text)

Max Activating Token Index: 269

Text #12

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8309. Min Act: -0.1699

Data Index: 2352331 (Open Web Text)

Max Activating Token Index: 666

Text #13

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8082. Min Act: -0.1699

Data Index: 3355107 (Open Web Text)

Max Activating Token Index: 1008

Text #14

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8034. Min Act: -0.1700

Data Index: 406732 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.7949. Min Act: -0.1695

Data Index: 6028768 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.7977. Min Act: -0.1694

Data Index: 8640716 (Open Web Text)

Max Activating Token Index: 1006

Text #17

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.8015. Min Act: -0.1700

Data Index: 7448287 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.7892. Min Act: -0.1700

Data Index: 767785 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 1.9259. Min Range: -1.9259

Max Act: 1.7841. Min Act: -0.1700

Data Index: 5583042 (Open Web Text)

Max Activating Token Index: 766