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

Dataset: The Pile

Neuron 2030 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.3026. Min Act: -0.0000

Data Index: 32663 (The Pile)

Max Activating Token Index: 211

Text #1

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1482630 (The Pile)

Max Activating Token Index: 191

Text #2

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2492. Min Act: -0.0000

Data Index: 468094 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2378. Min Act: -0.0000

Data Index: 812416 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1096094 (The Pile)

Max Activating Token Index: 658

Text #5

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2508. Min Act: -0.0000

Data Index: 1653208 (The Pile)

Max Activating Token Index: 752

Text #6

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2424. Min Act: -0.0000

Data Index: 980447 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1367371 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1696974 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2569. Min Act: -0.0000

Data Index: 541938 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1608487 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1109797 (The Pile)

Max Activating Token Index: 444

Text #12

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1561838 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2391. Min Act: -0.0000

Data Index: 272946 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.1834. Min Act: -0.0000

Data Index: 593321 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1399678 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2224. Min Act: -0.0000

Data Index: 274332 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2166. Min Act: -0.0000

Data Index: 354156 (The Pile)

Max Activating Token Index: 740

Text #18

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2210. Min Act: -0.0000

Data Index: 744783 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1171415 (The Pile)

Max Activating Token Index: 768