Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 347 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.2097. Min Act: -0.0002

Data Index: 674442 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.2037. Min Act: -0.0002

Data Index: 92510 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1748. Min Act: -0.0002

Data Index: 861028 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1632. Min Act: -0.0002

Data Index: 1034290 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1688. Min Act: -0.0002

Data Index: 648423 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1508. Min Act: -0.0002

Data Index: 490371 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1510. Min Act: -0.0002

Data Index: 868106 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1521. Min Act: -0.0002

Data Index: 597853 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1512. Min Act: -0.0002

Data Index: 739571 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1455. Min Act: -0.0002

Data Index: 528017 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1393. Min Act: -0.0002

Data Index: 45810 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1441. Min Act: -0.0002

Data Index: 329989 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1424. Min Act: -0.0002

Data Index: 982330 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1436. Min Act: -0.0002

Data Index: 654728 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1300. Min Act: -0.0002

Data Index: 310694 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1294. Min Act: -0.0001

Data Index: 287864 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1285. Min Act: -0.0001

Data Index: 551338 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1223. Min Act: -0.0001

Data Index: 28395 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1312. Min Act: -0.0002

Data Index: 986236 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1296. Min Act: -0.0002

Data Index: 1319633 (C4 (Web Text))

Max Activating Token Index: 959