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

Dataset: The Pile

Neuron 4876 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: 0.4817. Min Range: -0.4817

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1629919 (The Pile)

Max Activating Token Index: 445

Text #1

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4497. Min Act: -0.0000

Data Index: 172884 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4185. Min Act: -0.0000

Data Index: 35964 (The Pile)

Max Activating Token Index: 313

Text #3

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3829. Min Act: -0.0000

Data Index: 728438 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4095. Min Act: -0.0000

Data Index: 938976 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4002. Min Act: -0.0000

Data Index: 452939 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1151306 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3965. Min Act: 0.0000

Data Index: 1918121 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3763. Min Act: -0.0000

Data Index: 926180 (The Pile)

Max Activating Token Index: 363

Text #9

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3617. Min Act: -0.0000

Data Index: 47822 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1985423 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3560. Min Act: 0.0000

Data Index: 1681257 (The Pile)

Max Activating Token Index: 202

Text #12

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3530. Min Act: -0.0000

Data Index: 637927 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1168748 (The Pile)

Max Activating Token Index: 1004

Text #14

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3625. Min Act: -0.0000

Data Index: 600791 (The Pile)

Max Activating Token Index: 943

Text #15

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1457559 (The Pile)

Max Activating Token Index: 340

Text #16

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1741042 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3223. Min Act: -0.0000

Data Index: 391371 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3297. Min Act: -0.0000

Data Index: 427978 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3168. Min Act: -0.0000

Data Index: 168893 (The Pile)

Max Activating Token Index: 617