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

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

Neuron 650 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2413. Min Act: -0.0001

Data Index: 1140929 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2127. Min Act: -0.0001

Data Index: 137401 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2085. Min Act: -0.0001

Data Index: 1175049 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1678. Min Act: -0.0001

Data Index: 12444 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1548. Min Act: -0.0001

Data Index: 817426 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1727. Min Act: -0.0001

Data Index: 475323 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1725. Min Act: -0.0001

Data Index: 446555 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1718. Min Act: -0.0001

Data Index: 379825 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1633. Min Act: -0.0001

Data Index: 196654 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1524. Min Act: -0.0001

Data Index: 538506 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1250695 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1543. Min Act: -0.0001

Data Index: 556690 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1424. Min Act: -0.0001

Data Index: 221264 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1327683 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1353433 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1397. Min Act: -0.0001

Data Index: 219380 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1093183 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1354. Min Act: -0.0001

Data Index: 834688 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1345. Min Act: -0.0001

Data Index: 965058 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1471. Min Act: -0.0001

Data Index: 477013 (C4 (Web Text))

Max Activating Token Index: 271