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

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

Neuron 1552 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: 0.0436. Min Range: -0.0436

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1567 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0415. Min Act: -0.0002

Data Index: 36948 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1332657 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0393. Min Act: -0.0002

Data Index: 739614 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0382. Min Act: -0.0002

Data Index: 370117 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0380. Min Act: -0.0002

Data Index: 51969 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0369. Min Act: -0.0002

Data Index: 150437 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0372. Min Act: -0.0002

Data Index: 513115 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0365. Min Act: -0.0002

Data Index: 347754 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1096180 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0354. Min Act: -0.0002

Data Index: 341666 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0358. Min Act: -0.0002

Data Index: 893205 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0353. Min Act: -0.0002

Data Index: 380599 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0358. Min Act: -0.0002

Data Index: 37967 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0352. Min Act: -0.0002

Data Index: 302628 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1021919 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0343. Min Act: -0.0002

Data Index: 95630 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0343. Min Act: -0.0003

Data Index: 651816 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0350. Min Act: -0.0002

Data Index: 951888 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0338. Min Act: -0.0002

Data Index: 72007 (C4 (Web Text))

Max Activating Token Index: 354