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

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

Neuron 3853 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0306. Min Range: -2.0306

Max Act: 2.0306. Min Act: -0.0000

Data Index: 709931 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.7440. Min Act: -0.0000

Data Index: 843332 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.6956. Min Act: -0.0000

Data Index: 334659 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.4844. Min Act: -0.0000

Data Index: 1580826 (Python Code)

Max Activating Token Index: 335

Text #4

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.5322. Min Act: -0.0000

Data Index: 1116258 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.6333. Min Act: -0.0000

Data Index: 1120387 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.5072. Min Act: -0.0000

Data Index: 746231 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.4765. Min Act: -0.0000

Data Index: 1263226 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.4527. Min Act: -0.0000

Data Index: 207603 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.4373. Min Act: -0.0000

Data Index: 823660 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.3285. Min Act: -0.0000

Data Index: 663153 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.3862. Min Act: -0.0000

Data Index: 418417 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.3817. Min Act: -0.0000

Data Index: 1131316 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.3779. Min Act: -0.0000

Data Index: 155953 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.4460. Min Act: -0.0000

Data Index: 1335419 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.2831. Min Act: -0.0000

Data Index: 688236 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.2672. Min Act: -0.0000

Data Index: 625187 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.3467. Min Act: -0.0000

Data Index: 616698 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.4128. Min Act: -0.0000

Data Index: 460901 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 2.0306. Min Range: -2.0306

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1138904 (C4 (Web Text))

Max Activating Token Index: 594