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

Dataset: The Pile

Neuron 3877 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: 1.7666. Min Range: -1.7666

Max Act: 1.7666. Min Act: -0.0000

Data Index: 159114 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.3793. Min Act: -0.0000

Data Index: 1850049 (The Pile)

Max Activating Token Index: 721

Text #2

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.4616. Min Act: -0.0000

Data Index: 1145256 (The Pile)

Max Activating Token Index: 761

Text #3

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.4395. Min Act: -0.0000

Data Index: 1617563 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.4223. Min Act: -0.0000

Data Index: 1371027 (The Pile)

Max Activating Token Index: 493

Text #5

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.4356. Min Act: -0.0000

Data Index: 388190 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.4389. Min Act: -0.0000

Data Index: 265695 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.4063. Min Act: -0.0000

Data Index: 206288 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.3380. Min Act: -0.0000

Data Index: 1546504 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.3355. Min Act: -0.0000

Data Index: 485408 (The Pile)

Max Activating Token Index: 596

Text #10

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.3241. Min Act: -0.0000

Data Index: 860910 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1880173 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.3102. Min Act: -0.0000

Data Index: 431917 (The Pile)

Max Activating Token Index: 624

Text #13

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.3004. Min Act: -0.0000

Data Index: 1869203 (The Pile)

Max Activating Token Index: 548

Text #14

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.2818. Min Act: -0.0000

Data Index: 172646 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.2887. Min Act: -0.0000

Data Index: 1265626 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.2688. Min Act: -0.0000

Data Index: 635306 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.2695. Min Act: -0.0000

Data Index: 726750 (The Pile)

Max Activating Token Index: 951

Text #18

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1043401 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 1.7666. Min Range: -1.7666

Max Act: 1.1970. Min Act: -0.0000

Data Index: 518177 (The Pile)

Max Activating Token Index: 201