Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3053 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0004

Data Index: 431535 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0372. Min Act: -0.0004

Data Index: 1177461 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0421. Min Act: -0.0004

Data Index: 519696 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0391. Min Act: -0.0004

Data Index: 962145 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0390. Min Act: -0.0004

Data Index: 913038 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0382. Min Act: -0.0004

Data Index: 1133255 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0367. Min Act: -0.0004

Data Index: 257093 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0378. Min Act: -0.0004

Data Index: 822098 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0329. Min Act: -0.0004

Data Index: 1114564 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0369. Min Act: -0.0004

Data Index: 303289 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0366. Min Act: -0.0004

Data Index: 495191 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0371. Min Act: -0.0004

Data Index: 643357 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0364. Min Act: -0.0004

Data Index: 23587 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0358. Min Act: -0.0004

Data Index: 996390 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0348. Min Act: -0.0004

Data Index: 1013323 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0396. Min Act: -0.0004

Data Index: 110692 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0315. Min Act: -0.0004

Data Index: 227268 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0336. Min Act: -0.0004

Data Index: 350588 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0354. Min Act: -0.0004

Data Index: 617683 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0313. Min Act: -0.0004

Data Index: 1340115 (C4 (Web Text))

Max Activating Token Index: 579