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

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

Neuron 4349 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0000

Data Index: 2402 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0561. Min Act: -0.0000

Data Index: 576488 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0537. Min Act: -0.0000

Data Index: 108191 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1251224 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0504. Min Act: -0.0000

Data Index: 1304040 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0450. Min Act: -0.0000

Data Index: 822501 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0527. Min Act: -0.0000

Data Index: 532913 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1266749 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1241453 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0442. Min Act: -0.0000

Data Index: 1272161 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0446. Min Act: -0.0000

Data Index: 981723 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0402. Min Act: -0.0000

Data Index: 402986 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0478. Min Act: -0.0000

Data Index: 1631548 (Python Code)

Max Activating Token Index: 126

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0331. Min Act: -0.0000

Data Index: 1547878 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0449. Min Act: -0.0000

Data Index: 1556914 (Python Code)

Max Activating Token Index: 102

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0408. Min Act: -0.0000

Data Index: 289400 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0405. Min Act: -0.0000

Data Index: 273454 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1428411 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0292. Min Act: -0.0000

Data Index: 600892 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0479. Min Act: -0.0000

Data Index: 1032707 (C4 (Web Text))

Max Activating Token Index: 367