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

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

Neuron 1552 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1002963 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1950. Min Act: -0.0000

Data Index: 641167 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1651. Min Act: -0.0000

Data Index: 502363 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1689. Min Act: -0.0000

Data Index: 206601 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1609. Min Act: -0.0001

Data Index: 924896 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1158674 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1477. Min Act: -0.0000

Data Index: 23713 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1515. Min Act: -0.0000

Data Index: 686598 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1356. Min Act: -0.0000

Data Index: 946113 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1386. Min Act: -0.0001

Data Index: 160294 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1376. Min Act: -0.0000

Data Index: 450899 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1348. Min Act: -0.0001

Data Index: 847867 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1387511 (Python Code)

Max Activating Token Index: 787

Text #13

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1267. Min Act: -0.0000

Data Index: 568030 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1248. Min Act: -0.0001

Data Index: 446112 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1265. Min Act: -0.0000

Data Index: 625417 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1165205 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1024002 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1039016 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1232. Min Act: -0.0000

Data Index: 1287451 (C4 (Web Text))

Max Activating Token Index: 726