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

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

Neuron 4975 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: 0.1576. Min Range: -0.1576

Max Act: 0.1444. Min Act: -0.0001

Data Index: 602864 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1476182 (Python Code)

Max Activating Token Index: 803

Text #2

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1532. Min Act: -0.0001

Data Index: 470065 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1438. Min Act: -0.0001

Data Index: 608106 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1441. Min Act: -0.0001

Data Index: 434499 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1459. Min Act: -0.0001

Data Index: 558731 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1448353 (Python Code)

Max Activating Token Index: 505

Text #7

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1491. Min Act: -0.0001

Data Index: 466018 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1443. Min Act: -0.0001

Data Index: 1099313 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1353. Min Act: -0.0001

Data Index: 841713 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1386. Min Act: -0.0001

Data Index: 31528 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1331. Min Act: -0.0001

Data Index: 911818 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1546800 (Python Code)

Max Activating Token Index: 172

Text #13

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1304. Min Act: -0.0001

Data Index: 524210 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1355. Min Act: -0.0001

Data Index: 470768 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1203411 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1271. Min Act: -0.0001

Data Index: 488490 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1533164 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1380176 (Python Code)

Max Activating Token Index: 660

Text #19

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1300. Min Act: -0.0001

Data Index: 840928 (C4 (Web Text))

Max Activating Token Index: 124