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

Dataset: Open Web Text

Neuron 1028 in Layer 5

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: 4.2974. Min Range: -4.2974

Max Act: 4.2974. Min Act: -0.1700

Data Index: 835068 (Open Web Text)

Max Activating Token Index: 167

Text #1

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.1834. Min Act: -0.1700

Data Index: 6953817 (Open Web Text)

Max Activating Token Index: 660

Text #2

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.1642. Min Act: -0.1700

Data Index: 7688795 (Open Web Text)

Max Activating Token Index: 808

Text #3

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.1287. Min Act: -0.1700

Data Index: 4762327 (Open Web Text)

Max Activating Token Index: 359

Text #4

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.1607. Min Act: -0.1700

Data Index: 905254 (Open Web Text)

Max Activating Token Index: 51

Text #5

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.0920. Min Act: -0.1700

Data Index: 7531910 (Open Web Text)

Max Activating Token Index: 323

Text #6

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.1259. Min Act: -0.1700

Data Index: 4079378 (Open Web Text)

Max Activating Token Index: 981

Text #7

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.0536. Min Act: -0.1700

Data Index: 4788135 (Open Web Text)

Max Activating Token Index: 219

Text #8

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.0562. Min Act: -0.1700

Data Index: 4492725 (Open Web Text)

Max Activating Token Index: 166

Text #9

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.0501. Min Act: -0.1700

Data Index: 7628566 (Open Web Text)

Max Activating Token Index: 710

Text #10

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.0568. Min Act: -0.1700

Data Index: 4896266 (Open Web Text)

Max Activating Token Index: 881

Text #11

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.0272. Min Act: -0.1700

Data Index: 7881468 (Open Web Text)

Max Activating Token Index: 1013

Text #12

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.0225. Min Act: -0.1700

Data Index: 6343343 (Open Web Text)

Max Activating Token Index: 312

Text #13

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.0543. Min Act: -0.1700

Data Index: 7084860 (Open Web Text)

Max Activating Token Index: 999

Text #14

Max Range: 4.2974. Min Range: -4.2974

Max Act: 3.9847. Min Act: -0.1700

Data Index: 2183381 (Open Web Text)

Max Activating Token Index: 789

Text #15

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.0230. Min Act: -0.1700

Data Index: 3931509 (Open Web Text)

Max Activating Token Index: 381

Text #16

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.0308. Min Act: -0.1700

Data Index: 1886259 (Open Web Text)

Max Activating Token Index: 927

Text #17

Max Range: 4.2974. Min Range: -4.2974

Max Act: 4.0414. Min Act: -0.1700

Data Index: 2939821 (Open Web Text)

Max Activating Token Index: 102

Text #18

Max Range: 4.2974. Min Range: -4.2974

Max Act: 3.9961. Min Act: -0.1700

Data Index: 6838710 (Open Web Text)

Max Activating Token Index: 662

Text #19

Max Range: 4.2974. Min Range: -4.2974

Max Act: 3.9967. Min Act: -0.1700

Data Index: 6864116 (Open Web Text)

Max Activating Token Index: 895