Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1934 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1786. Min Act: -0.0000

Data Index: 894049 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1796. Min Act: -0.0000

Data Index: 544027 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1655. Min Act: -0.0000

Data Index: 553013 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1516. Min Act: -0.0000

Data Index: 794775 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1566. Min Act: -0.0000

Data Index: 831506 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1369. Min Act: -0.0000

Data Index: 485449 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1463. Min Act: -0.0000

Data Index: 175987 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1459. Min Act: -0.0000

Data Index: 952814 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1289. Min Act: -0.0000

Data Index: 700565 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1380. Min Act: -0.0000

Data Index: 725951 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1273040 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1072. Min Act: -0.0000

Data Index: 784972 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0979. Min Act: -0.0000

Data Index: 133437 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0487. Min Act: -0.0000

Data Index: 55879 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1235498 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0469. Min Act: -0.0000

Data Index: 1616777 (Python Code)

Max Activating Token Index: 478

Text #16

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0411. Min Act: -0.0000

Data Index: 891352 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1327594 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0430. Min Act: -0.0000

Data Index: 1193207 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0411. Min Act: -0.0000

Data Index: 1158781 (C4 (Web Text))

Max Activating Token Index: 656