Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2911 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0002

Data Index: 919065 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0216. Min Act: -0.0002

Data Index: 297717 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0212. Min Act: -0.0002

Data Index: 796921 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0214. Min Act: -0.0002

Data Index: 304685 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0214. Min Act: -0.0002

Data Index: 709340 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1589120 (Python Code)

Max Activating Token Index: 481

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0209. Min Act: -0.0002

Data Index: 235698 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0209. Min Act: -0.0002

Data Index: 159297 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0206. Min Act: -0.0002

Data Index: 964178 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1120411 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0207. Min Act: -0.0002

Data Index: 587865 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0204. Min Act: -0.0002

Data Index: 353727 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1284005 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0204. Min Act: -0.0002

Data Index: 349567 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0207. Min Act: -0.0002

Data Index: 942046 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0205. Min Act: -0.0002

Data Index: 322429 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0202. Min Act: -0.0003

Data Index: 233219 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1460765 (Python Code)

Max Activating Token Index: 456

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0205. Min Act: -0.0002

Data Index: 919592 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0204. Min Act: -0.0002

Data Index: 506886 (C4 (Web Text))

Max Activating Token Index: 353