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

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

Neuron 2359 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: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0002

Data Index: 699654 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1597984 (Python Code)

Max Activating Token Index: 907

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1471915 (Python Code)

Max Activating Token Index: 166

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0310. Min Act: -0.0002

Data Index: 793214 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1631104 (Python Code)

Max Activating Token Index: 751

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1444932 (Python Code)

Max Activating Token Index: 115

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1374955 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0292. Min Act: -0.0002

Data Index: 702496 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1568392 (Python Code)

Max Activating Token Index: 967

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1453266 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1564244 (Python Code)

Max Activating Token Index: 27

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1557195 (Python Code)

Max Activating Token Index: 776

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1485570 (Python Code)

Max Activating Token Index: 643

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1369409 (Python Code)

Max Activating Token Index: 295

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1614669 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0282. Min Act: -0.0002

Data Index: 633042 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1484488 (Python Code)

Max Activating Token Index: 108

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1567864 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1429570 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1564289 (Python Code)

Max Activating Token Index: 66