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

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

Neuron 2872 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: 0.3843. Min Range: -0.3843

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1020996 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1026562 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.3083. Min Act: -0.0000

Data Index: 580276 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2688. Min Act: -0.0000

Data Index: 501767 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2714. Min Act: -0.0000

Data Index: 374636 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2692. Min Act: -0.0000

Data Index: 780009 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1304633 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2145. Min Act: -0.0000

Data Index: 345983 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1225360 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1330272 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1080714 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1172160 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1050238 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2176. Min Act: -0.0000

Data Index: 268888 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.1955. Min Act: -0.0000

Data Index: 489402 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2039. Min Act: -0.0000

Data Index: 201509 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1278306 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.2003. Min Act: -0.0000

Data Index: 537083 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.1866. Min Act: -0.0000

Data Index: 917054 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.3843. Min Range: -0.3843

Max Act: 0.1877. Min Act: -0.0000

Data Index: 431947 (C4 (Web Text))

Max Activating Token Index: 620