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

Dataset: The Pile

Neuron 3067 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: 1.1906. Min Range: -1.1906

Max Act: 1.1906. Min Act: -0.0000

Data Index: 1310847 (The Pile)

Max Activating Token Index: 624

Text #1

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.1467. Min Act: -0.0000

Data Index: 15111 (The Pile)

Max Activating Token Index: 527

Text #2

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0633. Min Act: -0.0000

Data Index: 989600 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0467. Min Act: -0.0000

Data Index: 1669140 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0147. Min Act: -0.0000

Data Index: 485405 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.9929. Min Act: -0.0000

Data Index: 982279 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1832296 (The Pile)

Max Activating Token Index: 318

Text #7

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.9456. Min Act: -0.0000

Data Index: 196635 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1872592 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.9022. Min Act: -0.0000

Data Index: 799971 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1010794 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.9120. Min Act: -0.0000

Data Index: 318938 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.8226. Min Act: -0.0000

Data Index: 810067 (The Pile)

Max Activating Token Index: 714

Text #13

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1296050 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1782106 (The Pile)

Max Activating Token Index: 812

Text #15

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.8503. Min Act: -0.0000

Data Index: 525733 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1443877 (The Pile)

Max Activating Token Index: 490

Text #17

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.8893. Min Act: -0.0000

Data Index: 386462 (The Pile)

Max Activating Token Index: 251

Text #18

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1195318 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.8075. Min Act: -0.0000

Data Index: 19407 (The Pile)

Max Activating Token Index: 177