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

Dataset: The Pile

Neuron 3151 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6980. Min Range: -5.6980

Max Act: 5.6980. Min Act: -0.0000

Data Index: 764814 (The Pile)

Max Activating Token Index: 858

Text #1

Max Range: 5.6980. Min Range: -5.6980

Max Act: 5.4495. Min Act: -0.0000

Data Index: 1704571 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 5.6980. Min Range: -5.6980

Max Act: 5.2317. Min Act: -0.0000

Data Index: 1800167 (The Pile)

Max Activating Token Index: 132

Text #3

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.6120. Min Act: -0.0000

Data Index: 5715 (The Pile)

Max Activating Token Index: 583

Text #4

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.7776. Min Act: -0.0000

Data Index: 167900 (The Pile)

Max Activating Token Index: 593

Text #5

Max Range: 5.6980. Min Range: -5.6980

Max Act: 5.1282. Min Act: -0.0000

Data Index: 1251259 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.5422. Min Act: -0.0000

Data Index: 1428748 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.5579. Min Act: -0.0000

Data Index: 479921 (The Pile)

Max Activating Token Index: 952

Text #8

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.5936. Min Act: -0.0000

Data Index: 389186 (The Pile)

Max Activating Token Index: 858

Text #9

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.8556. Min Act: -0.0000

Data Index: 435755 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 5.6980. Min Range: -5.6980

Max Act: 5.0509. Min Act: -0.0000

Data Index: 1297784 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 5.6980. Min Range: -5.6980

Max Act: 5.0316. Min Act: -0.0000

Data Index: 926361 (The Pile)

Max Activating Token Index: 442

Text #12

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.4750. Min Act: -0.0000

Data Index: 181392 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.9801. Min Act: -0.0000

Data Index: 431815 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.5543. Min Act: -0.0000

Data Index: 258507 (The Pile)

Max Activating Token Index: 204

Text #15

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.4640. Min Act: -0.0000

Data Index: 878903 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.5062. Min Act: -0.0000

Data Index: 412090 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 5.6980. Min Range: -5.6980

Max Act: 3.6896. Min Act: -0.0000

Data Index: 372882 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.2221. Min Act: -0.0000

Data Index: 1654623 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 5.6980. Min Range: -5.6980

Max Act: 4.6894. Min Act: -0.0000

Data Index: 316273 (The Pile)

Max Activating Token Index: 842