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

Dataset: Open Web Text

Neuron 2467 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: 3.3266. Min Range: -3.3266

Max Act: 3.3266. Min Act: -0.1700

Data Index: 8795601 (Open Web Text)

Max Activating Token Index: 754

Text #1

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2291. Min Act: -0.1700

Data Index: 3248010 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0947. Min Act: -0.1700

Data Index: 5165090 (Open Web Text)

Max Activating Token Index: 383

Text #3

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0909. Min Act: -0.1700

Data Index: 6642913 (Open Web Text)

Max Activating Token Index: 610

Text #4

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0536. Min Act: -0.1700

Data Index: 8623582 (Open Web Text)

Max Activating Token Index: 187

Text #5

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0509. Min Act: -0.1700

Data Index: 8815482 (Open Web Text)

Max Activating Token Index: 402

Text #6

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0491. Min Act: -0.1700

Data Index: 8273455 (Open Web Text)

Max Activating Token Index: 311

Text #7

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0218. Min Act: -0.1700

Data Index: 6039774 (Open Web Text)

Max Activating Token Index: 828

Text #8

Max Range: 3.3266. Min Range: -3.3266

Max Act: 2.9440. Min Act: -0.1700

Data Index: 3949435 (Open Web Text)

Max Activating Token Index: 856

Text #9

Max Range: 3.3266. Min Range: -3.3266

Max Act: 2.9452. Min Act: -0.1700

Data Index: 1607895 (Open Web Text)

Max Activating Token Index: 515

Text #10

Max Range: 3.3266. Min Range: -3.3266

Max Act: 2.9348. Min Act: -0.1700

Data Index: 4339131 (Open Web Text)

Max Activating Token Index: 191

Text #11

Max Range: 3.3266. Min Range: -3.3266

Max Act: 2.9401. Min Act: -0.1700

Data Index: 8031730 (Open Web Text)

Max Activating Token Index: 699

Text #12

Max Range: 3.3266. Min Range: -3.3266

Max Act: 2.9185. Min Act: -0.1700

Data Index: 7042984 (Open Web Text)

Max Activating Token Index: 588

Text #13

Max Range: 3.3266. Min Range: -3.3266

Max Act: 2.9216. Min Act: -0.1700

Data Index: 1837009 (Open Web Text)

Max Activating Token Index: 759

Text #14

Max Range: 3.3266. Min Range: -3.3266

Max Act: 2.9293. Min Act: -0.1700

Data Index: 4409093 (Open Web Text)

Max Activating Token Index: 658

Text #15

Max Range: 3.3266. Min Range: -3.3266

Max Act: 2.9176. Min Act: -0.1700

Data Index: 6351679 (Open Web Text)

Max Activating Token Index: 285

Text #16

Max Range: 3.3266. Min Range: -3.3266

Max Act: 2.9146. Min Act: -0.1700

Data Index: 6257737 (Open Web Text)

Max Activating Token Index: 359

Text #17

Max Range: 3.3266. Min Range: -3.3266

Max Act: 2.9157. Min Act: -0.1700

Data Index: 5587019 (Open Web Text)

Max Activating Token Index: 668

Text #18

Max Range: 3.3266. Min Range: -3.3266

Max Act: 2.9085. Min Act: -0.1700

Data Index: 7238848 (Open Web Text)

Max Activating Token Index: 789

Text #19

Max Range: 3.3266. Min Range: -3.3266

Max Act: 2.8947. Min Act: -0.1700

Data Index: 4771130 (Open Web Text)

Max Activating Token Index: 769