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

Dataset: The Pile

Neuron 4375 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2541. Min Range: -3.2541

Max Act: 3.1227. Min Act: -0.0000

Data Index: 1747783 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 3.2541. Min Range: -3.2541

Max Act: 3.2541. Min Act: -0.0000

Data Index: 1042894 (The Pile)

Max Activating Token Index: 888

Text #2

Max Range: 3.2541. Min Range: -3.2541

Max Act: 3.0279. Min Act: -0.0000

Data Index: 1004759 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 3.2541. Min Range: -3.2541

Max Act: 3.0236. Min Act: -0.0000

Data Index: 973497 (The Pile)

Max Activating Token Index: 985

Text #4

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.6628. Min Act: -0.0000

Data Index: 1117583 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.4746. Min Act: -0.0000

Data Index: 833141 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.3621. Min Act: -0.0000

Data Index: 522386 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.7251. Min Act: -0.0000

Data Index: 1016368 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.5521. Min Act: -0.0000

Data Index: 691074 (The Pile)

Max Activating Token Index: 60

Text #9

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.5412. Min Act: -0.0000

Data Index: 672522 (The Pile)

Max Activating Token Index: 741

Text #10

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.6251. Min Act: -0.0000

Data Index: 1757860 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.6115. Min Act: -0.0000

Data Index: 388098 (The Pile)

Max Activating Token Index: 46

Text #12

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.4541. Min Act: -0.0000

Data Index: 1304487 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.3782. Min Act: -0.0000

Data Index: 276972 (The Pile)

Max Activating Token Index: 56

Text #14

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.4962. Min Act: -0.0000

Data Index: 1058056 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.3446. Min Act: -0.0000

Data Index: 90483 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.4632. Min Act: -0.0000

Data Index: 1459094 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.4578. Min Act: -0.0000

Data Index: 1101985 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.5872. Min Act: -0.0000

Data Index: 1403927 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 3.2541. Min Range: -3.2541

Max Act: 2.5450. Min Act: -0.0000

Data Index: 892803 (The Pile)

Max Activating Token Index: 998