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

Dataset: Open Web Text

Neuron 1511 in Layer 4

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: 1.8462. Min Range: -1.8462

Max Act: 1.8353. Min Act: -0.1700

Data Index: 3000708 (Open Web Text)

Max Activating Token Index: 309

Text #1

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.8462. Min Act: -0.1700

Data Index: 6183462 (Open Web Text)

Max Activating Token Index: 32

Text #2

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.8172. Min Act: -0.1700

Data Index: 500388 (Open Web Text)

Max Activating Token Index: 250

Text #3

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7922. Min Act: -0.1700

Data Index: 8283896 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7773. Min Act: -0.1700

Data Index: 6473389 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7909. Min Act: -0.1700

Data Index: 5448032 (Open Web Text)

Max Activating Token Index: 263

Text #6

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7578. Min Act: -0.1700

Data Index: 7992103 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7562. Min Act: -0.1700

Data Index: 6202799 (Open Web Text)

Max Activating Token Index: 665

Text #8

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7541. Min Act: -0.1700

Data Index: 4522261 (Open Web Text)

Max Activating Token Index: 789

Text #9

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7323. Min Act: -0.1700

Data Index: 4306369 (Open Web Text)

Max Activating Token Index: 116

Text #10

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7301. Min Act: -0.1700

Data Index: 8723101 (Open Web Text)

Max Activating Token Index: 916

Text #11

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7356. Min Act: -0.1700

Data Index: 8061051 (Open Web Text)

Max Activating Token Index: 137

Text #12

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7292. Min Act: -0.1700

Data Index: 6377297 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7227. Min Act: -0.1700

Data Index: 5869370 (Open Web Text)

Max Activating Token Index: 508

Text #14

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7017. Min Act: -0.1700

Data Index: 1486658 (Open Web Text)

Max Activating Token Index: 696

Text #15

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7280. Min Act: -0.1700

Data Index: 4675780 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7020. Min Act: -0.1700

Data Index: 3082543 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6960. Min Act: -0.1700

Data Index: 7841568 (Open Web Text)

Max Activating Token Index: 376

Text #18

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7218. Min Act: -0.1700

Data Index: 6180793 (Open Web Text)

Max Activating Token Index: 455

Text #19

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7059. Min Act: -0.1700

Data Index: 6274354 (Open Web Text)

Max Activating Token Index: 107