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

Dataset: The Pile

Neuron 3860 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: 1.1624. Min Range: -1.1624

Max Act: 1.1116. Min Act: -0.0000

Data Index: 505072 (The Pile)

Max Activating Token Index: 850

Text #1

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.1624. Min Act: -0.0000

Data Index: 1760790 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0110. Min Act: -0.0000

Data Index: 1686540 (The Pile)

Max Activating Token Index: 875

Text #3

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0712. Min Act: -0.0000

Data Index: 936654 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1073644 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8266. Min Act: -0.0000

Data Index: 442978 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1441448 (The Pile)

Max Activating Token Index: 917

Text #7

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9574. Min Act: -0.0000

Data Index: 771062 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0041. Min Act: -0.0000

Data Index: 543167 (The Pile)

Max Activating Token Index: 194

Text #9

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1452562 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9639. Min Act: -0.0000

Data Index: 899962 (The Pile)

Max Activating Token Index: 716

Text #11

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8951. Min Act: -0.0000

Data Index: 1992367 (The Pile)

Max Activating Token Index: 639

Text #12

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1331618 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8779. Min Act: -0.0000

Data Index: 183477 (The Pile)

Max Activating Token Index: 804

Text #14

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9333. Min Act: -0.0000

Data Index: 762824 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1722839 (The Pile)

Max Activating Token Index: 739

Text #16

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9156. Min Act: -0.0000

Data Index: 9017 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1039569 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1598625 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8771. Min Act: -0.0000

Data Index: 112258 (The Pile)

Max Activating Token Index: 808