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

Dataset: The Pile

Neuron 4888 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4518. Min Act: -0.0000

Data Index: 699632 (The Pile)

Max Activating Token Index: 933

Text #1

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4854. Min Act: -0.0000

Data Index: 1762792 (The Pile)

Max Activating Token Index: 228

Text #2

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1788582 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1644889 (The Pile)

Max Activating Token Index: 844

Text #4

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3984. Min Act: -0.0000

Data Index: 992631 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4103. Min Act: 0.0000

Data Index: 956195 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4043. Min Act: -0.0000

Data Index: 594934 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1799099 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4085. Min Act: 0.0000

Data Index: 1713718 (The Pile)

Max Activating Token Index: 988

Text #9

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4040. Min Act: -0.0000

Data Index: 986238 (The Pile)

Max Activating Token Index: 998

Text #10

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3564. Min Act: -0.0000

Data Index: 644203 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3499. Min Act: 0.0000

Data Index: 1196432 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3820. Min Act: -0.0000

Data Index: 495411 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1815960 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3578. Min Act: 0.0000

Data Index: 1379019 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3670. Min Act: -0.0000

Data Index: 206170 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1793298 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1090626 (The Pile)

Max Activating Token Index: 378

Text #18

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3493. Min Act: -0.0000

Data Index: 671320 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3183. Min Act: -0.0000

Data Index: 856575 (The Pile)

Max Activating Token Index: 834