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

Dataset: The Pile

Neuron 181 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: 0.3448. Min Range: -0.3448

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1534657 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3254. Min Act: -0.0000

Data Index: 1322226 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1220468 (The Pile)

Max Activating Token Index: 422

Text #3

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1368786 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2531. Min Act: -0.0000

Data Index: 84064 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2636. Min Act: -0.0000

Data Index: 519406 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2592. Min Act: -0.0000

Data Index: 35346 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2246. Min Act: -0.0000

Data Index: 3158 (The Pile)

Max Activating Token Index: 976

Text #8

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1435287 (The Pile)

Max Activating Token Index: 884

Text #9

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2494. Min Act: -0.0000

Data Index: 696191 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1846945 (The Pile)

Max Activating Token Index: 797

Text #11

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1708096 (The Pile)

Max Activating Token Index: 869

Text #12

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2640. Min Act: -0.0000

Data Index: 271383 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2385. Min Act: -0.0000

Data Index: 276611 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2353. Min Act: -0.0000

Data Index: 511699 (The Pile)

Max Activating Token Index: 618

Text #15

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1949933 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1218073 (The Pile)

Max Activating Token Index: 130

Text #17

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2348. Min Act: -0.0000

Data Index: 713690 (The Pile)

Max Activating Token Index: 975

Text #18

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1234659 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1005243 (The Pile)

Max Activating Token Index: 319