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

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

Neuron 2795 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0251. Min Range: -1.0251

Max Act: 1.0251. Min Act: -0.0001

Data Index: 701950 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.8989. Min Act: -0.0001

Data Index: 814624 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.8710. Min Act: -0.0001

Data Index: 1252282 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.8019. Min Act: -0.0001

Data Index: 952369 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.8121. Min Act: -0.0001

Data Index: 1181538 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7663. Min Act: -0.0001

Data Index: 251982 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7891. Min Act: -0.0001

Data Index: 184193 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7543. Min Act: -0.0001

Data Index: 270374 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7756. Min Act: -0.0001

Data Index: 993680 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7226. Min Act: -0.0001

Data Index: 167555 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7225. Min Act: -0.0001

Data Index: 330588 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7232. Min Act: -0.0001

Data Index: 538005 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7268. Min Act: -0.0001

Data Index: 708753 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6950. Min Act: -0.0001

Data Index: 690037 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6918. Min Act: -0.0001

Data Index: 692074 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6727. Min Act: -0.0001

Data Index: 1331862 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6866. Min Act: -0.0001

Data Index: 832548 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7090. Min Act: -0.0001

Data Index: 1251319 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7248. Min Act: -0.0001

Data Index: 1243198 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6141. Min Act: -0.0001

Data Index: 1030226 (C4 (Web Text))

Max Activating Token Index: 267