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

Dataset: The Pile

Neuron 3974 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: 1.2450. Min Range: -1.2450

Max Act: 1.2009. Min Act: -0.0000

Data Index: 1220507 (The Pile)

Max Activating Token Index: 303

Text #1

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.0688. Min Act: -0.0000

Data Index: 170590 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.2450. Min Act: -0.0000

Data Index: 1628096 (The Pile)

Max Activating Token Index: 781

Text #3

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1032888 (The Pile)

Max Activating Token Index: 156

Text #4

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.0620. Min Act: -0.0000

Data Index: 300004 (The Pile)

Max Activating Token Index: 775

Text #5

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.1297. Min Act: -0.0000

Data Index: 919582 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9180. Min Act: -0.0000

Data Index: 279088 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9849. Min Act: -0.0000

Data Index: 1696613 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9236. Min Act: -0.0000

Data Index: 595447 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9141. Min Act: -0.0000

Data Index: 200832 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9332. Min Act: -0.0000

Data Index: 355175 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1135576 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1661055 (The Pile)

Max Activating Token Index: 484

Text #13

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1027769 (The Pile)

Max Activating Token Index: 318

Text #14

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1553711 (The Pile)

Max Activating Token Index: 129

Text #15

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.8845. Min Act: -0.0000

Data Index: 252312 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1353225 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.8165. Min Act: -0.0000

Data Index: 998992 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1809709 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1926767 (The Pile)

Max Activating Token Index: 473