Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4806 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1386946 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1602. Min Act: -0.0000

Data Index: 449127 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1558081 (Python Code)

Max Activating Token Index: 552

Text #3

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1466119 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1374. Min Act: -0.0000

Data Index: 395639 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1497. Min Act: -0.0000

Data Index: 581222 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1468. Min Act: -0.0000

Data Index: 891679 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1654778 (Python Code)

Max Activating Token Index: 1005

Text #8

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1321. Min Act: -0.0000

Data Index: 566929 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1505. Min Act: -0.0000

Data Index: 141509 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1411303 (Python Code)

Max Activating Token Index: 663

Text #11

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1365942 (Python Code)

Max Activating Token Index: 392

Text #12

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1527163 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1404146 (Python Code)

Max Activating Token Index: 763

Text #14

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1322. Min Act: -0.0000

Data Index: 800510 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1582002 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1289. Min Act: -0.0000

Data Index: 76209 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1484278 (Python Code)

Max Activating Token Index: 363

Text #18

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1212. Min Act: -0.0000

Data Index: 159130 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1409905 (Python Code)

Max Activating Token Index: 626