Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 781 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0409. Min Act: -0.0001

Data Index: 676876 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0002

Data Index: 662176 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1600396 (Python Code)

Max Activating Token Index: 871

Text #3

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1099270 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0358. Min Act: -0.0002

Data Index: 972849 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0350. Min Act: -0.0003

Data Index: 1087625 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1028771 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0347. Min Act: -0.0000

Data Index: 959385 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0352. Min Act: -0.0003

Data Index: 826692 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1156804 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0345. Min Act: -0.0003

Data Index: 938967 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0342. Min Act: -0.0001

Data Index: 905592 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0349. Min Act: -0.0001

Data Index: 563320 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0347. Min Act: -0.0003

Data Index: 182985 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0340. Min Act: 0.0000

Data Index: 490749 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1019808 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0330. Min Act: -0.0003

Data Index: 129486 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1067153 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0315. Min Act: -0.0003

Data Index: 804410 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0336. Min Act: -0.0003

Data Index: 216108 (C4 (Web Text))

Max Activating Token Index: 250