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

Dataset: The Pile

Neuron 4558 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: 0.3864. Min Range: -0.3864

Max Act: 0.3580. Min Act: -0.0000

Data Index: 613752 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3850. Min Act: -0.0000

Data Index: 183028 (The Pile)

Max Activating Token Index: 96

Text #2

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1898008 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1443106 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1017486 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3627. Min Act: -0.0000

Data Index: 892098 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3468. Min Act: -0.0000

Data Index: 431063 (The Pile)

Max Activating Token Index: 158

Text #7

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3422. Min Act: -0.0000

Data Index: 641708 (The Pile)

Max Activating Token Index: 391

Text #8

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1201813 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3328. Min Act: -0.0000

Data Index: 422727 (The Pile)

Max Activating Token Index: 362

Text #10

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3381. Min Act: -0.0000

Data Index: 184331 (The Pile)

Max Activating Token Index: 445

Text #11

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3241. Min Act: -0.0000

Data Index: 264787 (The Pile)

Max Activating Token Index: 468

Text #12

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3337. Min Act: -0.0000

Data Index: 1035329 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3191. Min Act: -0.0000

Data Index: 460823 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.2891. Min Act: -0.0000

Data Index: 349659 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1938391 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3074. Min Act: -0.0000

Data Index: 893576 (The Pile)

Max Activating Token Index: 379

Text #17

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1484075 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.3104. Min Act: -0.0000

Data Index: 336196 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 0.3864. Min Range: -0.3864

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1663289 (The Pile)

Max Activating Token Index: 612