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

Dataset: The Pile

Neuron 3219 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: 1.2595. Min Range: -1.2595

Max Act: 1.1803. Min Act: -0.0000

Data Index: 1018580 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.1765. Min Act: -0.0000

Data Index: 11331 (The Pile)

Max Activating Token Index: 929

Text #2

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.2078. Min Act: -0.0000

Data Index: 809677 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1392086 (The Pile)

Max Activating Token Index: 579

Text #4

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.2595. Min Act: -0.0000

Data Index: 139799 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1677940 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0909. Min Act: -0.0000

Data Index: 1350766 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1734233 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0312. Min Act: -0.0000

Data Index: 1522179 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.2356. Min Act: -0.0000

Data Index: 1452357 (The Pile)

Max Activating Token Index: 943

Text #10

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0238. Min Act: -0.0000

Data Index: 1615194 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0252. Min Act: -0.0000

Data Index: 486098 (The Pile)

Max Activating Token Index: 432

Text #12

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1044705 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.1130. Min Act: -0.0000

Data Index: 1236376 (The Pile)

Max Activating Token Index: 986

Text #14

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1579990 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1766187 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0316. Min Act: -0.0000

Data Index: 997541 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.0001. Min Act: -0.0000

Data Index: 72833 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1853246 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9623. Min Act: -0.0000

Data Index: 1034397 (The Pile)

Max Activating Token Index: 778