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

Dataset: The Pile

Neuron 3022 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: 1.4153. Min Range: -1.4153

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1539259 (The Pile)

Max Activating Token Index: 570

Text #1

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.3901. Min Act: 0.0000

Data Index: 580510 (The Pile)

Max Activating Token Index: 62

Text #2

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.2879. Min Act: -0.0000

Data Index: 861248 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.3720. Min Act: -0.0000

Data Index: 453125 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1973553 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.2200. Min Act: -0.0000

Data Index: 540811 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.2002. Min Act: -0.0000

Data Index: 1136130 (The Pile)

Max Activating Token Index: 523

Text #7

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.1689. Min Act: -0.0000

Data Index: 1407786 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.2333. Min Act: -0.0000

Data Index: 1113506 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.1349. Min Act: -0.0000

Data Index: 96435 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.1507. Min Act: -0.0000

Data Index: 277962 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.0743. Min Act: -0.0000

Data Index: 282327 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1732330 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1603324 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.0705. Min Act: -0.0000

Data Index: 337795 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.9455. Min Act: -0.0000

Data Index: 442513 (The Pile)

Max Activating Token Index: 703

Text #16

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.0424. Min Act: -0.0000

Data Index: 1972808 (The Pile)

Max Activating Token Index: 790

Text #17

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.0285. Min Act: -0.0000

Data Index: 380304 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 1.4153. Min Range: -1.4153

Max Act: 1.0255. Min Act: -0.0000

Data Index: 437069 (The Pile)

Max Activating Token Index: 347

Text #19

Max Range: 1.4153. Min Range: -1.4153

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1125082 (The Pile)

Max Activating Token Index: 423