Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 946 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0001

Data Index: 527597 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0524. Min Act: 0.0003

Data Index: 285993 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0365. Min Act: -0.0001

Data Index: 399211 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0347. Min Act: -0.0000

Data Index: 628342 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0369. Min Act: -0.0000

Data Index: 145606 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0353. Min Act: -0.0000

Data Index: 506467 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0353. Min Act: -0.0001

Data Index: 146251 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0341. Min Act: 0.0000

Data Index: 512450 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0342. Min Act: 0.0001

Data Index: 1290660 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1119056 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0356. Min Act: 0.0002

Data Index: 368177 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0345. Min Act: -0.0000

Data Index: 635857 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0333. Min Act: -0.0000

Data Index: 311865 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0326. Min Act: 0.0003

Data Index: 1109247 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1159512 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0315. Min Act: -0.0001

Data Index: 593900 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1049638 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0308. Min Act: -0.0000

Data Index: 1303249 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0324. Min Act: -0.0000

Data Index: 904080 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0322. Min Act: -0.0001

Data Index: 863433 (C4 (Web Text))

Max Activating Token Index: 859