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

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

Neuron 3846 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.2036. Min Act: -0.0001

Data Index: 1201879 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1884. Min Act: -0.0001

Data Index: 290163 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1831. Min Act: -0.0001

Data Index: 1133287 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1791. Min Act: -0.0001

Data Index: 319925 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1729. Min Act: -0.0001

Data Index: 367540 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1740. Min Act: -0.0001

Data Index: 6726 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1743. Min Act: -0.0001

Data Index: 1333937 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1594. Min Act: -0.0001

Data Index: 603238 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1765. Min Act: -0.0001

Data Index: 653153 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1573. Min Act: -0.0001

Data Index: 958880 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1650. Min Act: -0.0001

Data Index: 993422 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1343. Min Act: -0.0001

Data Index: 769484 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1489. Min Act: -0.0002

Data Index: 344653 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1627. Min Act: -0.0002

Data Index: 1230976 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1237323 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1532. Min Act: -0.0001

Data Index: 129100 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1586. Min Act: -0.0001

Data Index: 869683 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1429. Min Act: -0.0001

Data Index: 997507 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1311. Min Act: -0.0002

Data Index: 595420 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.2036. Min Range: -0.2036

Max Act: 0.1350. Min Act: -0.0002

Data Index: 157545 (C4 (Web Text))

Max Activating Token Index: 455