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

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

Neuron 2890 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: 0.1749. Min Range: -0.1749

Max Act: 0.1749. Min Act: -0.0001

Data Index: 197924 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1486. Min Act: -0.0001

Data Index: 193236 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1566. Min Act: -0.0001

Data Index: 726412 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1474. Min Act: -0.0001

Data Index: 488162 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1453. Min Act: -0.0001

Data Index: 1079173 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1435. Min Act: -0.0001

Data Index: 240252 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1186366 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1064567 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1382. Min Act: -0.0001

Data Index: 662584 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1482. Min Act: -0.0001

Data Index: 657871 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1371. Min Act: -0.0001

Data Index: 998851 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1164916 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1417. Min Act: -0.0001

Data Index: 615201 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1320. Min Act: -0.0001

Data Index: 961072 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1302. Min Act: -0.0001

Data Index: 250526 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1354. Min Act: -0.0001

Data Index: 226407 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1300. Min Act: -0.0001

Data Index: 55748 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1287. Min Act: -0.0001

Data Index: 399641 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1386. Min Act: -0.0001

Data Index: 477786 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1368. Min Act: -0.0001

Data Index: 386794 (C4 (Web Text))

Max Activating Token Index: 867