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

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

Neuron 4482 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.5416. Min Act: -0.0000

Data Index: 1212736 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.4184. Min Act: -0.0000

Data Index: 123358 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.3183. Min Act: 0.0000

Data Index: 597764 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.3198. Min Act: -0.0000

Data Index: 987937 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2970. Min Act: -0.0000

Data Index: 131033 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.3579. Min Act: -0.0000

Data Index: 861293 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2763. Min Act: -0.0000

Data Index: 893720 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1342949 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2681. Min Act: -0.0000

Data Index: 1213533 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2586. Min Act: -0.0000

Data Index: 618407 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2174. Min Act: -0.0000

Data Index: 1314058 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2464. Min Act: 0.0001

Data Index: 2687 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2335. Min Act: -0.0000

Data Index: 304183 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2281. Min Act: -0.0000

Data Index: 1290534 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.2316. Min Act: -0.0000

Data Index: 701574 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.1746. Min Act: -0.0000

Data Index: 151045 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.1714. Min Act: -0.0000

Data Index: 450401 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.1582. Min Act: -0.0000

Data Index: 519985 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.1563. Min Act: 0.0001

Data Index: 60211 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 1.5416. Min Range: -1.5416

Max Act: 1.1564. Min Act: -0.0000

Data Index: 19347 (C4 (Web Text))

Max Activating Token Index: 480