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

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

Neuron 2920 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0482. Min Range: -1.0482

Max Act: 1.0482. Min Act: 0.0001

Data Index: 557540 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 1.0482. Min Range: -1.0482

Max Act: 1.0200. Min Act: 0.0000

Data Index: 740695 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 1.0482. Min Range: -1.0482

Max Act: 1.0318. Min Act: -0.0000

Data Index: 744677 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 1.0482. Min Range: -1.0482

Max Act: 1.0106. Min Act: -0.0000

Data Index: 736566 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8926. Min Act: 0.0001

Data Index: 241766 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.9005. Min Act: -0.0000

Data Index: 873496 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.9190. Min Act: 0.0000

Data Index: 776702 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.9722. Min Act: -0.0000

Data Index: 323767 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1088024 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8161. Min Act: 0.0001

Data Index: 105119 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8844. Min Act: -0.0000

Data Index: 314861 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8764. Min Act: -0.0000

Data Index: 518595 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8639. Min Act: -0.0000

Data Index: 332374 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1332233 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8366. Min Act: 0.0000

Data Index: 349321 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8586. Min Act: 0.0000

Data Index: 205991 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8479. Min Act: 0.0000

Data Index: 876912 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8215. Min Act: 0.0001

Data Index: 610919 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8335. Min Act: -0.0000

Data Index: 960797 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8020. Min Act: -0.0000

Data Index: 530255 (C4 (Web Text))

Max Activating Token Index: 127