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

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

Neuron 1914 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: 1.3603. Min Range: -1.3603

Max Act: 1.3603. Min Act: -0.0001

Data Index: 466167 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.3129. Min Act: -0.0000

Data Index: 32433 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.2319. Min Act: -0.0000

Data Index: 41626 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.2521. Min Act: -0.0000

Data Index: 406529 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1671. Min Act: -0.0000

Data Index: 418324 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.2258. Min Act: -0.0001

Data Index: 186910 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1448. Min Act: -0.0000

Data Index: 456548 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1621. Min Act: -0.0001

Data Index: 1266513 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1401. Min Act: -0.0000

Data Index: 924495 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0396. Min Act: -0.0001

Data Index: 676461 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0431. Min Act: -0.0001

Data Index: 1379389 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0569. Min Act: -0.0001

Data Index: 1539012 (Python Code)

Max Activating Token Index: 208

Text #12

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0585. Min Act: -0.0000

Data Index: 28558 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1407513 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0261. Min Act: 0.0001

Data Index: 1302742 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0219. Min Act: -0.0001

Data Index: 1031491 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9891. Min Act: -0.0000

Data Index: 639671 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9876. Min Act: -0.0001

Data Index: 1002561 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9024. Min Act: -0.0001

Data Index: 41213 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0709. Min Act: -0.0001

Data Index: 1019013 (C4 (Web Text))

Max Activating Token Index: 975