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

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

Neuron 2152 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0510. Min Act: -0.0002

Data Index: 96885 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0460. Min Act: -0.0002

Data Index: 861287 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0472. Min Act: -0.0002

Data Index: 734187 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0427. Min Act: -0.0002

Data Index: 937924 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0439. Min Act: -0.0002

Data Index: 215880 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0409. Min Act: -0.0002

Data Index: 350357 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0411. Min Act: -0.0002

Data Index: 867648 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0379. Min Act: -0.0002

Data Index: 234187 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0348. Min Act: -0.0002

Data Index: 184249 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0320. Min Act: -0.0002

Data Index: 761875 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0319. Min Act: -0.0002

Data Index: 704298 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0319. Min Act: -0.0002

Data Index: 854632 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0317. Min Act: -0.0002

Data Index: 221617 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0322. Min Act: -0.0002

Data Index: 555926 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0300. Min Act: -0.0002

Data Index: 457301 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0309. Min Act: -0.0002

Data Index: 64944 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0307. Min Act: -0.0002

Data Index: 671340 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1139069 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1240587 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0301. Min Act: -0.0002

Data Index: 363068 (C4 (Web Text))

Max Activating Token Index: 160