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

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

Neuron 1902 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: 0.2445. Min Range: -0.2445

Max Act: 0.2445. Min Act: -0.0001

Data Index: 613170 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2323. Min Act: -0.0000

Data Index: 642382 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1625. Min Act: -0.0001

Data Index: 258364 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1785. Min Act: -0.0001

Data Index: 776683 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1714. Min Act: -0.0001

Data Index: 644242 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1696. Min Act: -0.0001

Data Index: 35214 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1699. Min Act: -0.0001

Data Index: 175973 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1563. Min Act: -0.0001

Data Index: 805276 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1435. Min Act: -0.0001

Data Index: 1137438 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1564. Min Act: -0.0001

Data Index: 492630 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1459. Min Act: -0.0000

Data Index: 224986 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1366. Min Act: -0.0001

Data Index: 166768 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1401. Min Act: -0.0001

Data Index: 835662 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1383. Min Act: -0.0001

Data Index: 540661 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1387. Min Act: -0.0001

Data Index: 1071490 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1427. Min Act: -0.0001

Data Index: 408222 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1247021 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1383. Min Act: -0.0001

Data Index: 1175763 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1364. Min Act: -0.0001

Data Index: 1026199 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1298. Min Act: -0.0001

Data Index: 895578 (C4 (Web Text))

Max Activating Token Index: 834