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

Dataset: The Pile

Neuron 1724 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: 1.2572. Min Range: -1.2572

Max Act: 1.2572. Min Act: -0.0000

Data Index: 1543469 (The Pile)

Max Activating Token Index: 27

Text #1

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9979. Min Act: -0.0000

Data Index: 656102 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9902. Min Act: -0.0000

Data Index: 436905 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1195885 (The Pile)

Max Activating Token Index: 723

Text #4

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8599. Min Act: -0.0000

Data Index: 223595 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8246. Min Act: -0.0000

Data Index: 425334 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8251. Min Act: -0.0000

Data Index: 708083 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8305. Min Act: -0.0000

Data Index: 254039 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1393072 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.7713. Min Act: -0.0000

Data Index: 758167 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1840210 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1736439 (The Pile)

Max Activating Token Index: 834

Text #12

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.6413. Min Act: -0.0000

Data Index: 600591 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1723584 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1807914 (The Pile)

Max Activating Token Index: 91

Text #15

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.6308. Min Act: -0.0000

Data Index: 727932 (The Pile)

Max Activating Token Index: 868

Text #16

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.6065. Min Act: -0.0000

Data Index: 379089 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.6332. Min Act: -0.0000

Data Index: 987781 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.5918. Min Act: -0.0000

Data Index: 272442 (The Pile)

Max Activating Token Index: 277

Text #19

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.6214. Min Act: -0.0000

Data Index: 416953 (The Pile)

Max Activating Token Index: 996