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

Dataset: The Pile

Neuron 3347 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: 3.3212. Min Range: -3.3212

Max Act: 3.1832. Min Act: -0.0000

Data Index: 1873069 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 3.3212. Min Range: -3.3212

Max Act: 3.3212. Min Act: -0.0000

Data Index: 1365091 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.8666. Min Act: -0.0000

Data Index: 1088391 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 3.3212. Min Range: -3.3212

Max Act: 3.0088. Min Act: -0.0000

Data Index: 1028003 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.9154. Min Act: -0.0000

Data Index: 75501 (The Pile)

Max Activating Token Index: 859

Text #5

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.9074. Min Act: -0.0000

Data Index: 1137807 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.8882. Min Act: -0.0000

Data Index: 1657063 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.8841. Min Act: -0.0000

Data Index: 1136716 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.7478. Min Act: -0.0000

Data Index: 1589391 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.6859. Min Act: -0.0000

Data Index: 1078208 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.7095. Min Act: -0.0000

Data Index: 1455327 (The Pile)

Max Activating Token Index: 424

Text #11

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.6976. Min Act: -0.0000

Data Index: 1144259 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.6535. Min Act: -0.0000

Data Index: 141879 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.6210. Min Act: -0.0000

Data Index: 619590 (The Pile)

Max Activating Token Index: 610

Text #14

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.4449. Min Act: -0.0000

Data Index: 1631235 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.4799. Min Act: -0.0000

Data Index: 974256 (The Pile)

Max Activating Token Index: 177

Text #16

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.3523. Min Act: -0.0000

Data Index: 1335888 (The Pile)

Max Activating Token Index: 253

Text #17

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.3671. Min Act: -0.0000

Data Index: 659235 (The Pile)

Max Activating Token Index: 663

Text #18

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.4541. Min Act: -0.0000

Data Index: 42560 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 3.3212. Min Range: -3.3212

Max Act: 2.4257. Min Act: -0.0000

Data Index: 915784 (The Pile)

Max Activating Token Index: 140