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

Dataset: The Pile

Neuron 772 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.6981. Min Act: -0.0000

Data Index: 1190423 (The Pile)

Max Activating Token Index: 355

Text #1

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.4861. Min Act: -0.0000

Data Index: 1587459 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.4321. Min Act: -0.0000

Data Index: 1653156 (The Pile)

Max Activating Token Index: 977

Text #3

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1580127 (The Pile)

Max Activating Token Index: 189

Text #4

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.4017. Min Act: -0.0000

Data Index: 715541 (The Pile)

Max Activating Token Index: 336

Text #5

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.4125. Min Act: -0.0000

Data Index: 1869018 (The Pile)

Max Activating Token Index: 571

Text #6

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.4685. Min Act: -0.0000

Data Index: 1301376 (The Pile)

Max Activating Token Index: 319

Text #7

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.3658. Min Act: -0.0000

Data Index: 138771 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.3376. Min Act: -0.0000

Data Index: 1004323 (The Pile)

Max Activating Token Index: 352

Text #9

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.3189. Min Act: -0.0000

Data Index: 1931697 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.2745. Min Act: -0.0000

Data Index: 260030 (The Pile)

Max Activating Token Index: 716

Text #11

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.1996. Min Act: -0.0000

Data Index: 589196 (The Pile)

Max Activating Token Index: 696

Text #12

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.2632. Min Act: -0.0000

Data Index: 161263 (The Pile)

Max Activating Token Index: 494

Text #13

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.3246. Min Act: -0.0000

Data Index: 1742967 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.2334. Min Act: -0.0000

Data Index: 349522 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.2247. Min Act: -0.0000

Data Index: 1323342 (The Pile)

Max Activating Token Index: 805

Text #16

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.1463. Min Act: -0.0000

Data Index: 934502 (The Pile)

Max Activating Token Index: 511

Text #17

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.2944. Min Act: -0.0000

Data Index: 883876 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.1280. Min Act: -0.0000

Data Index: 1573325 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 1.6981. Min Range: -1.6981

Max Act: 1.1952. Min Act: -0.0000

Data Index: 1623827 (The Pile)

Max Activating Token Index: 230