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

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

Neuron 2100 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0002

Data Index: 399257 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0389. Min Act: -0.0002

Data Index: 306730 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0379. Min Act: -0.0002

Data Index: 311130 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0394. Min Act: -0.0002

Data Index: 564251 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1321727 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0375. Min Act: -0.0002

Data Index: 215767 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0368. Min Act: -0.0002

Data Index: 306183 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0362. Min Act: -0.0002

Data Index: 868966 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0360. Min Act: -0.0002

Data Index: 843851 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0345. Min Act: -0.0002

Data Index: 335238 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0354. Min Act: -0.0002

Data Index: 689860 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0351. Min Act: -0.0002

Data Index: 374981 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1253454 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0350. Min Act: -0.0002

Data Index: 48815 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1156654 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1157325 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0344. Min Act: -0.0002

Data Index: 483086 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0336. Min Act: -0.0002

Data Index: 573506 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0334. Min Act: -0.0002

Data Index: 650037 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0334. Min Act: -0.0002

Data Index: 286823 (C4 (Web Text))

Max Activating Token Index: 23