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

Dataset: The Pile

Neuron 1097 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1637981 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4796. Min Act: -0.0000

Data Index: 859648 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1205766 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1759402 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4413. Min Act: -0.0000

Data Index: 550530 (The Pile)

Max Activating Token Index: 38

Text #5

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1626595 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1471269 (The Pile)

Max Activating Token Index: 931

Text #7

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4063. Min Act: -0.0000

Data Index: 172565 (The Pile)

Max Activating Token Index: 337

Text #8

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3996. Min Act: -0.0000

Data Index: 1664076 (The Pile)

Max Activating Token Index: 501

Text #9

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4104. Min Act: -0.0000

Data Index: 556153 (The Pile)

Max Activating Token Index: 203

Text #10

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1036808 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1577125 (The Pile)

Max Activating Token Index: 517

Text #12

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1143089 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1164682 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1382946 (The Pile)

Max Activating Token Index: 767

Text #15

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1352632 (The Pile)

Max Activating Token Index: 743

Text #16

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1631696 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3709. Min Act: -0.0000

Data Index: 579425 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1412243 (The Pile)

Max Activating Token Index: 892

Text #19

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1020365 (The Pile)

Max Activating Token Index: 911