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

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

Neuron 4607 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0354. Min Act: -0.0002

Data Index: 575647 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0002

Data Index: 22517 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0347. Min Act: -0.0002

Data Index: 262032 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0363. Min Act: -0.0002

Data Index: 179890 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1107466 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0268. Min Act: -0.0002

Data Index: 589814 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0341. Min Act: -0.0002

Data Index: 700838 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1067998 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1569894 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0002

Data Index: 439947 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1187812 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0333. Min Act: -0.0002

Data Index: 117059 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1386314 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1326876 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1139563 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0318. Min Act: -0.0002

Data Index: 346484 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0302. Min Act: -0.0002

Data Index: 950046 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1436095 (Python Code)

Max Activating Token Index: 912

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0263. Min Act: -0.0002

Data Index: 12239 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1573490 (Python Code)

Max Activating Token Index: 585