Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 20 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1070378 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1629. Min Act: -0.0001

Data Index: 111599 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1105094 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1177761 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1467. Min Act: -0.0002

Data Index: 149341 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1431. Min Act: -0.0002

Data Index: 966663 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1425. Min Act: -0.0001

Data Index: 740099 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1420. Min Act: -0.0001

Data Index: 807704 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1322355 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1395. Min Act: -0.0001

Data Index: 149613 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1419. Min Act: -0.0001

Data Index: 354718 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1384. Min Act: -0.0001

Data Index: 999038 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1361. Min Act: -0.0001

Data Index: 427438 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1357. Min Act: -0.0001

Data Index: 1100469 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1368. Min Act: -0.0001

Data Index: 137620 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1324. Min Act: -0.0001

Data Index: 630181 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1333. Min Act: -0.0001

Data Index: 1206081 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1319. Min Act: -0.0001

Data Index: 567263 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1297. Min Act: -0.0001

Data Index: 292144 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1281. Min Act: -0.0001

Data Index: 675060 (C4 (Web Text))

Max Activating Token Index: 662