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

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

Neuron 2402 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.9059. Min Act: -0.0000

Data Index: 885713 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.7567. Min Act: -0.0000

Data Index: 222819 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.7084. Min Act: -0.0000

Data Index: 614935 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.7140. Min Act: -0.0000

Data Index: 635237 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.6891. Min Act: -0.0000

Data Index: 1388342 (Python Code)

Max Activating Token Index: 470

Text #5

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.4952. Min Act: -0.0000

Data Index: 301013 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.3503. Min Act: -0.0000

Data Index: 1488797 (Python Code)

Max Activating Token Index: 427

Text #7

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.2690. Min Act: -0.0000

Data Index: 191521 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.3212. Min Act: -0.0000

Data Index: 1491173 (Python Code)

Max Activating Token Index: 611

Text #9

Max Range: 1.9059. Min Range: -1.9059

Max Act: 0.9892. Min Act: -0.0000

Data Index: 1556744 (Python Code)

Max Activating Token Index: 458

Text #10

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.2514. Min Act: -0.0000

Data Index: 674286 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1442300 (Python Code)

Max Activating Token Index: 547

Text #12

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.2536. Min Act: -0.0000

Data Index: 738895 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.1776. Min Act: -0.0000

Data Index: 213141 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1570438 (Python Code)

Max Activating Token Index: 764

Text #15

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1583657 (Python Code)

Max Activating Token Index: 332

Text #16

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.2567. Min Act: -0.0000

Data Index: 1033255 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.0823. Min Act: -0.0000

Data Index: 1361558 (Python Code)

Max Activating Token Index: 387

Text #18

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.1191. Min Act: -0.0000

Data Index: 1476382 (Python Code)

Max Activating Token Index: 828

Text #19

Max Range: 1.9059. Min Range: -1.9059

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1523045 (Python Code)

Max Activating Token Index: 196