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

Dataset: The Pile

Neuron 4530 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.7671. Min Act: -0.0000

Data Index: 1750667 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.6446. Min Act: -0.0000

Data Index: 1267048 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.3227. Min Act: -0.0000

Data Index: 1383244 (The Pile)

Max Activating Token Index: 608

Text #3

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.6278. Min Act: -0.0000

Data Index: 898740 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.5506. Min Act: -0.0000

Data Index: 869875 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.5027. Min Act: -0.0000

Data Index: 818789 (The Pile)

Max Activating Token Index: 470

Text #6

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.3460. Min Act: -0.0000

Data Index: 535028 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.4925. Min Act: -0.0000

Data Index: 1398868 (The Pile)

Max Activating Token Index: 432

Text #8

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.3319. Min Act: -0.0000

Data Index: 1777211 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.3174. Min Act: -0.0000

Data Index: 1606968 (The Pile)

Max Activating Token Index: 168

Text #10

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.2937. Min Act: -0.0000

Data Index: 1285343 (The Pile)

Max Activating Token Index: 380

Text #11

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.4248. Min Act: -0.0000

Data Index: 61755 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.4074. Min Act: -0.0000

Data Index: 712814 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.4109. Min Act: -0.0000

Data Index: 1338428 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.5515. Min Act: -0.0000

Data Index: 1062032 (The Pile)

Max Activating Token Index: 904

Text #15

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.7031. Min Act: -0.0000

Data Index: 846095 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.3519. Min Act: -0.0000

Data Index: 1298863 (The Pile)

Max Activating Token Index: 597

Text #17

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.3838. Min Act: -0.0000

Data Index: 1450623 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.3532. Min Act: -0.0000

Data Index: 365638 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 3.7671. Min Range: -3.7671

Max Act: 3.2075. Min Act: -0.0000

Data Index: 271603 (The Pile)

Max Activating Token Index: 602