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

Dataset: Open Web Text

Neuron 1653 in Layer 1

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: 0.6788. Min Range: -0.6788

Max Act: 0.6788. Min Act: -0.1700

Data Index: 4256608 (Open Web Text)

Max Activating Token Index: 350

Text #1

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6661. Min Act: -0.1700

Data Index: 6443620 (Open Web Text)

Max Activating Token Index: 330

Text #2

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6609. Min Act: -0.1700

Data Index: 4845286 (Open Web Text)

Max Activating Token Index: 312

Text #3

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6622. Min Act: -0.1700

Data Index: 6853739 (Open Web Text)

Max Activating Token Index: 297

Text #4

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6517. Min Act: -0.1700

Data Index: 5947313 (Open Web Text)

Max Activating Token Index: 327

Text #5

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6492. Min Act: -0.1700

Data Index: 2573206 (Open Web Text)

Max Activating Token Index: 338

Text #6

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6390. Min Act: -0.1700

Data Index: 2730133 (Open Web Text)

Max Activating Token Index: 306

Text #7

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6426. Min Act: -0.1700

Data Index: 3404699 (Open Web Text)

Max Activating Token Index: 314

Text #8

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6419. Min Act: -0.1700

Data Index: 7824582 (Open Web Text)

Max Activating Token Index: 310

Text #9

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6365. Min Act: -0.1700

Data Index: 1853441 (Open Web Text)

Max Activating Token Index: 328

Text #10

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6304. Min Act: -0.1700

Data Index: 3155653 (Open Web Text)

Max Activating Token Index: 325

Text #11

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6308. Min Act: -0.1700

Data Index: 588341 (Open Web Text)

Max Activating Token Index: 286

Text #12

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6344. Min Act: -0.1700

Data Index: 3211655 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6317. Min Act: -0.1700

Data Index: 3335277 (Open Web Text)

Max Activating Token Index: 312

Text #14

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6315. Min Act: -0.1700

Data Index: 6980055 (Open Web Text)

Max Activating Token Index: 323

Text #15

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6225. Min Act: -0.1699

Data Index: 3168161 (Open Web Text)

Max Activating Token Index: 308

Text #16

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6273. Min Act: -0.1700

Data Index: 170450 (Open Web Text)

Max Activating Token Index: 325

Text #17

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6203. Min Act: -0.1700

Data Index: 22846 (Open Web Text)

Max Activating Token Index: 281

Text #18

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6270. Min Act: -0.1700

Data Index: 3451710 (Open Web Text)

Max Activating Token Index: 278

Text #19

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6240. Min Act: -0.1700

Data Index: 1618049 (Open Web Text)

Max Activating Token Index: 316