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

Dataset: The Pile

Neuron 1888 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.3352. Min Act: -0.0000

Data Index: 789261 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2930. Min Act: -0.0000

Data Index: 515377 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1909999 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1414898 (The Pile)

Max Activating Token Index: 343

Text #4

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2826. Min Act: -0.0000

Data Index: 713337 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.3012. Min Act: -0.0000

Data Index: 33910 (The Pile)

Max Activating Token Index: 528

Text #6

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2720. Min Act: -0.0000

Data Index: 321552 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1384923 (The Pile)

Max Activating Token Index: 224

Text #8

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1548919 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2490. Min Act: -0.0000

Data Index: 5876 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.1762. Min Act: -0.0000

Data Index: 758125 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1769603 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1662710 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1223088 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1995301 (The Pile)

Max Activating Token Index: 408

Text #15

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1425099 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2224. Min Act: -0.0000

Data Index: 810419 (The Pile)

Max Activating Token Index: 608

Text #17

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.1918. Min Act: -0.0000

Data Index: 184831 (The Pile)

Max Activating Token Index: 991

Text #18

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1439471 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2238. Min Act: -0.0000

Data Index: 150494 (The Pile)

Max Activating Token Index: 468