Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 800 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0386. Min Act: -0.0003

Data Index: 912497 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1020482 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0330. Min Act: -0.0003

Data Index: 161076 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1094478 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0315. Min Act: -0.0004

Data Index: 575651 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0325. Min Act: -0.0003

Data Index: 274963 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0343. Min Act: -0.0003

Data Index: 364316 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0320. Min Act: -0.0003

Data Index: 220135 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0300. Min Act: -0.0003

Data Index: 943402 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0309. Min Act: -0.0003

Data Index: 587778 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0347. Min Act: -0.0004

Data Index: 757582 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0309. Min Act: -0.0004

Data Index: 263848 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0308. Min Act: -0.0003

Data Index: 297101 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0314. Min Act: -0.0003

Data Index: 959951 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0294. Min Act: -0.0003

Data Index: 588197 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0312. Min Act: -0.0003

Data Index: 542708 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0303. Min Act: -0.0003

Data Index: 477896 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0307. Min Act: -0.0003

Data Index: 333943 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0305. Min Act: -0.0003

Data Index: 669424 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0296. Min Act: -0.0003

Data Index: 647905 (C4 (Web Text))

Max Activating Token Index: 421