Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1306 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0487. Min Act: -0.0003

Data Index: 118248 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1157884 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0433. Min Act: -0.0003

Data Index: 394675 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0424. Min Act: -0.0003

Data Index: 63127 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0388. Min Act: -0.0003

Data Index: 171421 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1136253 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0356. Min Act: -0.0003

Data Index: 357369 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0401. Min Act: -0.0003

Data Index: 374286 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0375. Min Act: -0.0003

Data Index: 925381 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0337. Min Act: -0.0003

Data Index: 939317 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0374. Min Act: -0.0003

Data Index: 277325 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0358. Min Act: -0.0003

Data Index: 691150 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0361. Min Act: -0.0003

Data Index: 213967 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1296370 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1019511 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0336. Min Act: -0.0002

Data Index: 477945 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0341. Min Act: -0.0003

Data Index: 868546 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1257488 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0347. Min Act: -0.0003

Data Index: 110080 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0329. Min Act: -0.0003

Data Index: 16221 (C4 (Web Text))

Max Activating Token Index: 301