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

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

Neuron 3245 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1122045 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1217928 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2434. Min Act: -0.0000

Data Index: 162678 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2420. Min Act: -0.0001

Data Index: 250299 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1003529 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2324. Min Act: -0.0001

Data Index: 1258553 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2305. Min Act: -0.0000

Data Index: 335648 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2280. Min Act: -0.0001

Data Index: 139791 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1028280 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1027642 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2413. Min Act: -0.0000

Data Index: 742353 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2414. Min Act: -0.0000

Data Index: 642065 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2214. Min Act: -0.0000

Data Index: 1414134 (Python Code)

Max Activating Token Index: 888

Text #13

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2290. Min Act: -0.0000

Data Index: 100218 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2278. Min Act: -0.0001

Data Index: 527746 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1289017 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1247735 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2240. Min Act: -0.0000

Data Index: 58526 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2275. Min Act: -0.0000

Data Index: 126338 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2185. Min Act: -0.0000

Data Index: 338308 (C4 (Web Text))

Max Activating Token Index: 363