Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1214 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.2299. Min Act: -0.0003

Data Index: 1166705 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.2297. Min Act: -0.0003

Data Index: 408230 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1662. Min Act: -0.0003

Data Index: 656874 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1636. Min Act: -0.0003

Data Index: 421578 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1605. Min Act: -0.0003

Data Index: 81188 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1590. Min Act: -0.0003

Data Index: 542265 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1528. Min Act: -0.0003

Data Index: 512537 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1571. Min Act: -0.0003

Data Index: 1071162 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1465. Min Act: -0.0003

Data Index: 406812 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1678. Min Act: -0.0003

Data Index: 272016 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1453. Min Act: -0.0003

Data Index: 1055452 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1347. Min Act: -0.0003

Data Index: 172747 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1545. Min Act: -0.0003

Data Index: 100220 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1535. Min Act: -0.0003

Data Index: 611891 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1585. Min Act: -0.0003

Data Index: 258986 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1467. Min Act: -0.0003

Data Index: 1318336 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1402. Min Act: -0.0003

Data Index: 688782 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1634. Min Act: -0.0003

Data Index: 1068757 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1622. Min Act: -0.0003

Data Index: 318845 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1549. Min Act: -0.0003

Data Index: 742295 (C4 (Web Text))

Max Activating Token Index: 574