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

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

Neuron 3545 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2408. Min Act: -0.0000

Data Index: 390180 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1795. Min Act: -0.0000

Data Index: 958590 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1967. Min Act: -0.0000

Data Index: 62492 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2401. Min Act: -0.0000

Data Index: 86100 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1260108 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1691. Min Act: -0.0000

Data Index: 668600 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1671. Min Act: -0.0000

Data Index: 445130 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1123754 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1605. Min Act: -0.0000

Data Index: 106345 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1030620 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1452. Min Act: -0.0001

Data Index: 139893 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1306. Min Act: -0.0000

Data Index: 659827 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1418. Min Act: -0.0000

Data Index: 737760 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1225031 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1354. Min Act: -0.0000

Data Index: 608691 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1326. Min Act: -0.0000

Data Index: 698157 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1042434 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1395. Min Act: -0.0000

Data Index: 177996 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1302. Min Act: -0.0001

Data Index: 610083 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1123. Min Act: -0.0000

Data Index: 786626 (C4 (Web Text))

Max Activating Token Index: 1004