Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 379 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1601222 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8395. Min Act: -0.0000

Data Index: 434944 (The Pile)

Max Activating Token Index: 1005

Text #2

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1770106 (The Pile)

Max Activating Token Index: 412

Text #3

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.7127. Min Act: -0.0000

Data Index: 310393 (The Pile)

Max Activating Token Index: 271

Text #4

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6652. Min Act: -0.0000

Data Index: 640971 (The Pile)

Max Activating Token Index: 905

Text #5

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1863188 (The Pile)

Max Activating Token Index: 364

Text #6

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6260. Min Act: -0.0000

Data Index: 688603 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6752. Min Act: -0.0000

Data Index: 262375 (The Pile)

Max Activating Token Index: 487

Text #8

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6309. Min Act: -0.0000

Data Index: 313857 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5954. Min Act: -0.0000

Data Index: 627646 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5957. Min Act: -0.0000

Data Index: 204617 (The Pile)

Max Activating Token Index: 744

Text #11

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1993264 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1816024 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5674. Min Act: -0.0000

Data Index: 21242 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1044994 (The Pile)

Max Activating Token Index: 399

Text #15

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5677. Min Act: -0.0000

Data Index: 698521 (The Pile)

Max Activating Token Index: 183

Text #16

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1865534 (The Pile)

Max Activating Token Index: 476

Text #17

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5783. Min Act: -0.0000

Data Index: 604425 (The Pile)

Max Activating Token Index: 677

Text #18

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5571. Min Act: -0.0000

Data Index: 302344 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5069. Min Act: -0.0000

Data Index: 178301 (The Pile)

Max Activating Token Index: 374