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

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

Neuron 3131 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.4646. Min Act: -0.0000

Data Index: 905577 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.2317. Min Act: -0.0000

Data Index: 424479 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.2153. Min Act: -0.0000

Data Index: 109920 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0966. Min Act: -0.0000

Data Index: 496601 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0592. Min Act: 0.0001

Data Index: 264827 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0400. Min Act: 0.0000

Data Index: 1337241 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0126. Min Act: -0.0000

Data Index: 1345024 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0119. Min Act: -0.0000

Data Index: 768916 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1039785 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9216. Min Act: 0.0001

Data Index: 555383 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9326. Min Act: -0.0000

Data Index: 926047 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9032. Min Act: -0.0000

Data Index: 303255 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1132706 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.8536. Min Act: -0.0000

Data Index: 297992 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.8888. Min Act: -0.0000

Data Index: 986178 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.8669. Min Act: -0.0000

Data Index: 343572 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1638 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.8513. Min Act: -0.0000

Data Index: 677509 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.8227. Min Act: -0.0000

Data Index: 138409 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.8349. Min Act: -0.0000

Data Index: 306980 (C4 (Web Text))

Max Activating Token Index: 401