Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1790 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1183814 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1513160 (Python Code)

Max Activating Token Index: 564

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1371808 (Python Code)

Max Activating Token Index: 376

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1426242 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1281. Min Act: -0.0001

Data Index: 624564 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1228874 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1436. Min Act: -0.0001

Data Index: 1336047 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1334. Min Act: -0.0001

Data Index: 994426 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1225. Min Act: -0.0001

Data Index: 94576 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1335. Min Act: -0.0000

Data Index: 267985 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1303. Min Act: -0.0000

Data Index: 41057 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1278. Min Act: -0.0000

Data Index: 96259 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1648048 (Python Code)

Max Activating Token Index: 191

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1260. Min Act: -0.0001

Data Index: 653445 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1250. Min Act: -0.0000

Data Index: 233602 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1281. Min Act: -0.0001

Data Index: 73629 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1189. Min Act: -0.0000

Data Index: 46515 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1411373 (Python Code)

Max Activating Token Index: 959

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1088420 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1262. Min Act: -0.0001

Data Index: 672483 (C4 (Web Text))

Max Activating Token Index: 463