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

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

Neuron 3612 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: 0.6714. Min Range: -0.6714

Max Act: 0.6714. Min Act: -0.0001

Data Index: 328141 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6469. Min Act: -0.0001

Data Index: 188408 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6511. Min Act: -0.0000

Data Index: 988485 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6235. Min Act: -0.0001

Data Index: 1158975 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5911. Min Act: -0.0001

Data Index: 921920 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6177. Min Act: -0.0001

Data Index: 1092175 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5750. Min Act: -0.0001

Data Index: 1246444 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5272. Min Act: -0.0001

Data Index: 1231396 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6002. Min Act: -0.0001

Data Index: 767184 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5335. Min Act: -0.0001

Data Index: 1023134 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5525. Min Act: -0.0001

Data Index: 8522 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5346. Min Act: -0.0001

Data Index: 664374 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5500. Min Act: -0.0000

Data Index: 762352 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5537. Min Act: -0.0001

Data Index: 1318925 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5490. Min Act: -0.0001

Data Index: 83806 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5348. Min Act: -0.0001

Data Index: 1140721 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5621. Min Act: -0.0001

Data Index: 767188 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5416. Min Act: -0.0001

Data Index: 1126559 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1133849 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5284. Min Act: -0.0001

Data Index: 952739 (C4 (Web Text))

Max Activating Token Index: 557