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

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

Neuron 307 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0412. Min Act: -0.0006

Data Index: 950526 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1284944 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0374. Min Act: -0.0006

Data Index: 1335497 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0389. Min Act: -0.0006

Data Index: 513869 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0338. Min Act: -0.0005

Data Index: 241485 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0345. Min Act: -0.0006

Data Index: 48049 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0351. Min Act: -0.0006

Data Index: 766864 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0364. Min Act: -0.0006

Data Index: 866316 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0344. Min Act: -0.0006

Data Index: 61609 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0342. Min Act: -0.0006

Data Index: 138956 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0327. Min Act: -0.0006

Data Index: 1302701 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0332. Min Act: -0.0006

Data Index: 869818 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0331. Min Act: -0.0006

Data Index: 1006314 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0329. Min Act: -0.0006

Data Index: 1103084 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0321. Min Act: -0.0006

Data Index: 249668 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0332. Min Act: -0.0006

Data Index: 733379 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0315. Min Act: -0.0005

Data Index: 1017091 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0322. Min Act: -0.0006

Data Index: 753384 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0322. Min Act: -0.0006

Data Index: 687624 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0320. Min Act: -0.0006

Data Index: 943201 (C4 (Web Text))

Max Activating Token Index: 33