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

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

Neuron 1058 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1900. Min Act: -0.0001

Data Index: 167330 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1859. Min Act: -0.0001

Data Index: 1138165 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1183416 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1605. Min Act: -0.0001

Data Index: 107584 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1574. Min Act: -0.0001

Data Index: 1244987 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1470. Min Act: -0.0001

Data Index: 974006 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1151433 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1553. Min Act: -0.0001

Data Index: 109635 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1694. Min Act: -0.0001

Data Index: 35705 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1655807 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1310. Min Act: -0.0001

Data Index: 60292 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1409. Min Act: -0.0001

Data Index: 621738 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1419. Min Act: -0.0001

Data Index: 27245 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1053121 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1365. Min Act: -0.0001

Data Index: 834895 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1366. Min Act: -0.0001

Data Index: 622547 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1380. Min Act: -0.0001

Data Index: 893712 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1346658 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1318362 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1385. Min Act: -0.0001

Data Index: 432524 (C4 (Web Text))

Max Activating Token Index: 595