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

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

Neuron 1143 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: 0.0329. Min Range: -0.0329

Max Act: 0.0318. Min Act: -0.0006

Data Index: 132214 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0324. Min Act: -0.0006

Data Index: 1328560 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0006

Data Index: 2633 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0300. Min Act: -0.0006

Data Index: 928761 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0286. Min Act: -0.0006

Data Index: 545612 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0304. Min Act: -0.0006

Data Index: 1308109 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0298. Min Act: -0.0006

Data Index: 434845 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0286. Min Act: -0.0006

Data Index: 788565 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0291. Min Act: -0.0006

Data Index: 72996 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0289. Min Act: -0.0006

Data Index: 749247 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0288. Min Act: -0.0006

Data Index: 435504 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0277. Min Act: -0.0006

Data Index: 547670 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0306. Min Act: -0.0006

Data Index: 653273 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0298. Min Act: -0.0005

Data Index: 1299892 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0292. Min Act: -0.0006

Data Index: 932 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0286. Min Act: -0.0006

Data Index: 46450 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0286. Min Act: -0.0006

Data Index: 582927 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0290. Min Act: -0.0006

Data Index: 1267566 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0295. Min Act: -0.0006

Data Index: 301393 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0268. Min Act: -0.0006

Data Index: 635848 (C4 (Web Text))

Max Activating Token Index: 904