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

Dataset: The Pile

Neuron 1169 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: 1.3988. Min Range: -1.3988

Max Act: 1.3578. Min Act: -0.0000

Data Index: 380621 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.3988. Min Act: -0.0000

Data Index: 389564 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.3640. Min Act: -0.0000

Data Index: 651401 (The Pile)

Max Activating Token Index: 293

Text #3

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.2833. Min Act: -0.0000

Data Index: 620562 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.2660. Min Act: -0.0000

Data Index: 1430198 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.2854. Min Act: -0.0000

Data Index: 1289110 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.3239. Min Act: 0.0000

Data Index: 1498084 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.2516. Min Act: -0.0000

Data Index: 872339 (The Pile)

Max Activating Token Index: 232

Text #8

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.2103. Min Act: -0.0000

Data Index: 1522023 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.1555. Min Act: -0.0000

Data Index: 213262 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.2015. Min Act: -0.0000

Data Index: 1721057 (The Pile)

Max Activating Token Index: 310

Text #11

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.1112. Min Act: -0.0000

Data Index: 1781190 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.1170. Min Act: -0.0000

Data Index: 854316 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.1779. Min Act: -0.0000

Data Index: 1398756 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.1524. Min Act: -0.0000

Data Index: 352048 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.1303. Min Act: -0.0000

Data Index: 671708 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.2170. Min Act: -0.0000

Data Index: 1436613 (The Pile)

Max Activating Token Index: 817

Text #17

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.2383. Min Act: -0.0000

Data Index: 288315 (The Pile)

Max Activating Token Index: 273

Text #18

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1912017 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.1430. Min Act: -0.0000

Data Index: 654378 (The Pile)

Max Activating Token Index: 292