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

Dataset: The Pile

Neuron 4068 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: 0.9946. Min Range: -0.9946

Max Act: 0.9946. Min Act: -0.0000

Data Index: 959209 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1110726 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1740137 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1334754 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.6660. Min Act: -0.0000

Data Index: 833196 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5943. Min Act: -0.0000

Data Index: 331068 (The Pile)

Max Activating Token Index: 271

Text #6

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5975. Min Act: 0.0001

Data Index: 957412 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5922. Min Act: -0.0000

Data Index: 353331 (The Pile)

Max Activating Token Index: 539

Text #8

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5629. Min Act: -0.0000

Data Index: 748187 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5937. Min Act: 0.0001

Data Index: 308740 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1762580 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5524. Min Act: -0.0000

Data Index: 425511 (The Pile)

Max Activating Token Index: 742

Text #12

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5604. Min Act: -0.0000

Data Index: 325007 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5553. Min Act: 0.0000

Data Index: 1927417 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5472. Min Act: -0.0000

Data Index: 50695 (The Pile)

Max Activating Token Index: 536

Text #15

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5791. Min Act: -0.0000

Data Index: 222592 (The Pile)

Max Activating Token Index: 751

Text #16

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5643. Min Act: 0.0000

Data Index: 1328592 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1147887 (The Pile)

Max Activating Token Index: 322

Text #18

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5382. Min Act: 0.0000

Data Index: 1650371 (The Pile)

Max Activating Token Index: 992

Text #19

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.5284. Min Act: -0.0000

Data Index: 437011 (The Pile)

Max Activating Token Index: 361