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

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

Neuron 286 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: 0.2577. Min Range: -0.2577

Max Act: 0.2577. Min Act: -0.0002

Data Index: 637796 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2471. Min Act: -0.0002

Data Index: 986262 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2348. Min Act: -0.0002

Data Index: 173140 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2181. Min Act: -0.0002

Data Index: 745990 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2156. Min Act: -0.0002

Data Index: 431401 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2064. Min Act: -0.0002

Data Index: 168022 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1912. Min Act: -0.0002

Data Index: 591537 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2126. Min Act: -0.0002

Data Index: 1342078 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2192. Min Act: -0.0002

Data Index: 1293505 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2121. Min Act: -0.0002

Data Index: 325536 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2015. Min Act: -0.0002

Data Index: 1255609 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2100. Min Act: -0.0002

Data Index: 594382 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2068. Min Act: -0.0002

Data Index: 420899 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2075. Min Act: -0.0002

Data Index: 1207807 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1990. Min Act: -0.0002

Data Index: 8200 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1965. Min Act: -0.0002

Data Index: 654035 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2024. Min Act: -0.0002

Data Index: 225232 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2013. Min Act: -0.0001

Data Index: 1352263 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1994. Min Act: -0.0002

Data Index: 726784 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1921. Min Act: -0.0002

Data Index: 57664 (C4 (Web Text))

Max Activating Token Index: 114