Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 393 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1157463 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1136493 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1942345 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4339. Min Act: -0.0000

Data Index: 210406 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1450392 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4098. Min Act: -0.0000

Data Index: 99693 (The Pile)

Max Activating Token Index: 345

Text #6

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1348160 (The Pile)

Max Activating Token Index: 953

Text #7

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4146. Min Act: -0.0000

Data Index: 966795 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4238. Min Act: -0.0000

Data Index: 14071 (The Pile)

Max Activating Token Index: 464

Text #9

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1379394 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1702554 (The Pile)

Max Activating Token Index: 930

Text #11

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1746424 (The Pile)

Max Activating Token Index: 476

Text #12

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4171. Min Act: -0.0000

Data Index: 393260 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1337360 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1233101 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1884353 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1847000 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3691. Min Act: -0.0000

Data Index: 409676 (The Pile)

Max Activating Token Index: 411

Text #18

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1294055 (The Pile)

Max Activating Token Index: 533

Text #19

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3904. Min Act: -0.0000

Data Index: 234841 (The Pile)

Max Activating Token Index: 631