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

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

Neuron 1863 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.2026. Min Act: -0.0000

Data Index: 1357299 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.2038. Min Act: -0.0001

Data Index: 116085 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.1270. Min Act: -0.0000

Data Index: 175126 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0941. Min Act: -0.0000

Data Index: 553269 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0789. Min Act: -0.0000

Data Index: 1222444 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0013. Min Act: -0.0000

Data Index: 462748 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0238. Min Act: -0.0001

Data Index: 1123368 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0001. Min Act: -0.0000

Data Index: 304725 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1142788 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0021. Min Act: -0.0001

Data Index: 857438 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.9242. Min Act: -0.0000

Data Index: 227959 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.9767. Min Act: -0.0000

Data Index: 936152 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.9423. Min Act: -0.0001

Data Index: 78850 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.9068. Min Act: -0.0000

Data Index: 920770 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.9016. Min Act: -0.0001

Data Index: 112452 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.8715. Min Act: -0.0000

Data Index: 647124 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.8407. Min Act: -0.0000

Data Index: 8742 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1317606 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.8239. Min Act: -0.0000

Data Index: 105094 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1130133 (C4 (Web Text))

Max Activating Token Index: 588