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

Dataset: The Pile

Neuron 1461 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: 1.3448. Min Range: -1.3448

Max Act: 1.3448. Min Act: -0.0000

Data Index: 294181 (The Pile)

Max Activating Token Index: 789

Text #1

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.3440. Min Act: -0.0000

Data Index: 96089 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.2989. Min Act: -0.0000

Data Index: 674762 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.3042. Min Act: -0.0000

Data Index: 568466 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.2760. Min Act: -0.0000

Data Index: 347774 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1094865 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.2688. Min Act: -0.0000

Data Index: 642381 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.1994. Min Act: -0.0000

Data Index: 1504537 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.1980. Min Act: -0.0000

Data Index: 994183 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.1625. Min Act: -0.0000

Data Index: 667131 (The Pile)

Max Activating Token Index: 534

Text #10

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.1635. Min Act: -0.0000

Data Index: 872166 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.1674. Min Act: -0.0000

Data Index: 1705555 (The Pile)

Max Activating Token Index: 455

Text #12

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.1999. Min Act: -0.0000

Data Index: 1261151 (The Pile)

Max Activating Token Index: 905

Text #13

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1266376 (The Pile)

Max Activating Token Index: 219

Text #14

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1422430 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.0849. Min Act: -0.0000

Data Index: 1462877 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.1213. Min Act: -0.0000

Data Index: 311768 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.0829. Min Act: -0.0000

Data Index: 396261 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1959118 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.1406. Min Act: -0.0000

Data Index: 984601 (The Pile)

Max Activating Token Index: 1017