Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4752 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0121. Min Range: -4.0121

Max Act: 4.0121. Min Act: -0.0000

Data Index: 937081 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.2031. Min Act: -0.0000

Data Index: 168515 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.3628. Min Act: -0.0000

Data Index: 286367 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.9671. Min Act: -0.0000

Data Index: 944132 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.9196. Min Act: -0.0000

Data Index: 401027 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.5639. Min Act: -0.0000

Data Index: 561368 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.6012. Min Act: -0.0000

Data Index: 607779 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.7413. Min Act: -0.0000

Data Index: 979472 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.6917. Min Act: -0.0000

Data Index: 1287600 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.4140. Min Act: -0.0000

Data Index: 170447 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.2778. Min Act: -0.0000

Data Index: 903768 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.3400. Min Act: -0.0000

Data Index: 1228514 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.3107. Min Act: -0.0000

Data Index: 293943 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.3665. Min Act: -0.0000

Data Index: 594906 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.2425. Min Act: -0.0000

Data Index: 811605 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.2370. Min Act: -0.0000

Data Index: 711905 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.3419. Min Act: -0.0000

Data Index: 1142445 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.1859. Min Act: -0.0000

Data Index: 1221234 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.1367. Min Act: -0.0000

Data Index: 306774 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 4.0121. Min Range: -4.0121

Max Act: 2.1186. Min Act: -0.0000

Data Index: 541819 (C4 (Web Text))

Max Activating Token Index: 531