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

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

Neuron 4353 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2596. Min Act: -0.0001

Data Index: 1436821 (Python Code)

Max Activating Token Index: 933

Text #1

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2380. Min Act: -0.0001

Data Index: 1647290 (Python Code)

Max Activating Token Index: 170

Text #2

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1481732 (Python Code)

Max Activating Token Index: 459

Text #3

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2644. Min Act: -0.0001

Data Index: 1444821 (Python Code)

Max Activating Token Index: 823

Text #4

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2277. Min Act: -0.0001

Data Index: 1645852 (Python Code)

Max Activating Token Index: 379

Text #5

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2424. Min Act: -0.0001

Data Index: 1376984 (Python Code)

Max Activating Token Index: 588

Text #6

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1417874 (Python Code)

Max Activating Token Index: 287

Text #7

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2323. Min Act: -0.0001

Data Index: 1473422 (Python Code)

Max Activating Token Index: 408

Text #8

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2659. Min Act: -0.0001

Data Index: 1616190 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2116. Min Act: -0.0001

Data Index: 1441030 (Python Code)

Max Activating Token Index: 656

Text #10

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1921. Min Act: -0.0001

Data Index: 1369364 (Python Code)

Max Activating Token Index: 627

Text #11

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2057. Min Act: -0.0001

Data Index: 1456679 (Python Code)

Max Activating Token Index: 331

Text #12

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2395. Min Act: -0.0001

Data Index: 1617539 (Python Code)

Max Activating Token Index: 711

Text #13

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2208. Min Act: -0.0001

Data Index: 1490722 (Python Code)

Max Activating Token Index: 694

Text #14

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2567. Min Act: -0.0001

Data Index: 1524183 (Python Code)

Max Activating Token Index: 672

Text #15

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2413. Min Act: -0.0001

Data Index: 1610566 (Python Code)

Max Activating Token Index: 105

Text #16

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2413. Min Act: -0.0001

Data Index: 1655704 (Python Code)

Max Activating Token Index: 936

Text #17

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2335. Min Act: -0.0001

Data Index: 1572374 (Python Code)

Max Activating Token Index: 701

Text #18

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2071. Min Act: -0.0001

Data Index: 1465420 (Python Code)

Max Activating Token Index: 185

Text #19

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2364. Min Act: -0.0001

Data Index: 1454845 (Python Code)

Max Activating Token Index: 372