Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 680 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4577. Min Range: -3.4577

Max Act: 3.4577. Min Act: -0.0000

Data Index: 73150 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.9105. Min Act: -0.0000

Data Index: 286572 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.8753. Min Act: -0.0001

Data Index: 1246898 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.6217. Min Act: -0.0001

Data Index: 1307624 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.5170. Min Act: -0.0001

Data Index: 1326292 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.4191. Min Act: -0.0001

Data Index: 462000 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.5862. Min Act: -0.0000

Data Index: 558178 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.4532. Min Act: -0.0001

Data Index: 177505 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.4162. Min Act: -0.0001

Data Index: 1238684 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.4369. Min Act: -0.0000

Data Index: 57776 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.4210. Min Act: -0.0000

Data Index: 733452 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.3474. Min Act: -0.0001

Data Index: 910159 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.3221. Min Act: -0.0001

Data Index: 291778 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.2838. Min Act: -0.0000

Data Index: 142079 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.2654. Min Act: -0.0001

Data Index: 511189 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.3278. Min Act: -0.0001

Data Index: 1297560 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.3232. Min Act: -0.0001

Data Index: 1356831 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.1901. Min Act: -0.0001

Data Index: 1185018 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.1697. Min Act: -0.0001

Data Index: 689846 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 3.4577. Min Range: -3.4577

Max Act: 2.0539. Min Act: -0.0001

Data Index: 305310 (C4 (Web Text))

Max Activating Token Index: 890