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

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

Neuron 3749 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4588. Min Act: -0.0001

Data Index: 1161468 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.5242. Min Act: -0.0000

Data Index: 1334926 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4246. Min Act: -0.0001

Data Index: 591043 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4564. Min Act: -0.0000

Data Index: 1308250 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4403. Min Act: -0.0001

Data Index: 273582 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3528. Min Act: -0.0001

Data Index: 1351812 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3530. Min Act: -0.0001

Data Index: 1052067 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2504. Min Act: -0.0001

Data Index: 55801 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2204. Min Act: -0.0001

Data Index: 522134 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1695. Min Act: -0.0001

Data Index: 1208135 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1295. Min Act: -0.0001

Data Index: 1249770 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2200. Min Act: -0.0001

Data Index: 1008681 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1422. Min Act: -0.0000

Data Index: 762413 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1851. Min Act: -0.0001

Data Index: 441973 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1785. Min Act: -0.0000

Data Index: 413944 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1302. Min Act: -0.0001

Data Index: 1200094 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0432. Min Act: -0.0000

Data Index: 590174 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0541. Min Act: -0.0000

Data Index: 20301 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0788. Min Act: -0.0001

Data Index: 257976 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0040. Min Act: -0.0001

Data Index: 1219898 (C4 (Web Text))

Max Activating Token Index: 416