Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 966 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0426. Min Act: -0.0003

Data Index: 618293 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0426. Min Act: -0.0002

Data Index: 487896 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1307990 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1358190 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0387. Min Act: -0.0004

Data Index: 566038 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1064521 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0380. Min Act: -0.0002

Data Index: 568150 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0374. Min Act: -0.0003

Data Index: 755832 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0361. Min Act: -0.0002

Data Index: 272798 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0360. Min Act: -0.0003

Data Index: 71091 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0363. Min Act: -0.0003

Data Index: 112960 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0360. Min Act: -0.0002

Data Index: 815967 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0361. Min Act: -0.0003

Data Index: 981650 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0350. Min Act: -0.0002

Data Index: 469527 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0358. Min Act: -0.0003

Data Index: 932339 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1123593 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0351. Min Act: -0.0003

Data Index: 593667 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0340. Min Act: -0.0003

Data Index: 934837 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0337. Min Act: -0.0003

Data Index: 585476 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0344. Min Act: -0.0003

Data Index: 630168 (C4 (Web Text))

Max Activating Token Index: 672