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

Dataset: The Pile

Neuron 3432 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: 1.4968. Min Range: -1.4968

Max Act: 1.4968. Min Act: -0.0000

Data Index: 1629314 (The Pile)

Max Activating Token Index: 426

Text #1

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.4218. Min Act: -0.0000

Data Index: 1502861 (The Pile)

Max Activating Token Index: 37

Text #2

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1299154 (The Pile)

Max Activating Token Index: 338

Text #3

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.4709. Min Act: -0.0000

Data Index: 1143736 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1364349 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.3973. Min Act: -0.0000

Data Index: 1453389 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1928. Min Act: -0.0000

Data Index: 1450152 (The Pile)

Max Activating Token Index: 974

Text #7

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.2299. Min Act: -0.0000

Data Index: 1392046 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.2482. Min Act: -0.0000

Data Index: 1248448 (The Pile)

Max Activating Token Index: 490

Text #9

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1914. Min Act: -0.0000

Data Index: 1348038 (The Pile)

Max Activating Token Index: 512

Text #10

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1449. Min Act: -0.0000

Data Index: 1817681 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1695. Min Act: -0.0000

Data Index: 1943291 (The Pile)

Max Activating Token Index: 442

Text #12

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1688562 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1759. Min Act: -0.0000

Data Index: 939642 (The Pile)

Max Activating Token Index: 343

Text #14

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1591. Min Act: -0.0000

Data Index: 1320075 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1500. Min Act: -0.0000

Data Index: 903772 (The Pile)

Max Activating Token Index: 185

Text #16

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.2885. Min Act: -0.0000

Data Index: 1499538 (The Pile)

Max Activating Token Index: 768

Text #17

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1791575 (The Pile)

Max Activating Token Index: 214

Text #18

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.2234. Min Act: -0.0000

Data Index: 483785 (The Pile)

Max Activating Token Index: 979

Text #19

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1920239 (The Pile)

Max Activating Token Index: 569