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

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

Neuron 1991 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: 0.1882. Min Range: -0.1882

Max Act: 0.1882. Min Act: -0.0001

Data Index: 627070 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1748. Min Act: -0.0001

Data Index: 1317208 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1566. Min Act: -0.0001

Data Index: 325198 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1604. Min Act: -0.0001

Data Index: 47555 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1522. Min Act: -0.0001

Data Index: 662773 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1365. Min Act: -0.0001

Data Index: 966497 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1304. Min Act: -0.0001

Data Index: 357557 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1455. Min Act: -0.0001

Data Index: 715219 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1111960 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1262. Min Act: 0.0000

Data Index: 528125 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1251. Min Act: -0.0001

Data Index: 794916 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1290. Min Act: -0.0001

Data Index: 977510 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1217884 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1278. Min Act: -0.0001

Data Index: 751090 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1271. Min Act: -0.0001

Data Index: 568561 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1254. Min Act: -0.0001

Data Index: 577729 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1244. Min Act: -0.0001

Data Index: 414620 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1196. Min Act: -0.0001

Data Index: 5435 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1235. Min Act: -0.0001

Data Index: 157315 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1179. Min Act: -0.0001

Data Index: 987659 (C4 (Web Text))

Max Activating Token Index: 225