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

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

Neuron 4226 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.4403. Min Act: -0.0000

Data Index: 584532 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.3716. Min Act: -0.0000

Data Index: 296542 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.3275. Min Act: -0.0000

Data Index: 1292329 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.2437. Min Act: -0.0000

Data Index: 1187268 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.2221. Min Act: -0.0000

Data Index: 409657 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.1663. Min Act: -0.0000

Data Index: 540534 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.1852. Min Act: -0.0000

Data Index: 1136997 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.1800. Min Act: -0.0000

Data Index: 706217 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.1751. Min Act: -0.0000

Data Index: 1073389 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.1441. Min Act: -0.0000

Data Index: 13908 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.1369. Min Act: -0.0000

Data Index: 520633 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.1126. Min Act: -0.0000

Data Index: 824473 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.0727. Min Act: -0.0000

Data Index: 1265490 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.0415. Min Act: -0.0000

Data Index: 405448 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.0343. Min Act: -0.0000

Data Index: 1013683 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.0371. Min Act: -0.0000

Data Index: 240314 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.0983. Min Act: -0.0000

Data Index: 897802 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.0547. Min Act: -0.0000

Data Index: 280455 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.1196. Min Act: -0.0000

Data Index: 520164 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 1.4403. Min Range: -1.4403

Max Act: 1.0363. Min Act: -0.0000

Data Index: 793551 (C4 (Web Text))

Max Activating Token Index: 206