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

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

Neuron 4505 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2835. Min Act: -0.0000

Data Index: 638087 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1094129 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2380. Min Act: -0.0000

Data Index: 963636 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2258. Min Act: -0.0000

Data Index: 441525 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2364. Min Act: -0.0000

Data Index: 695885 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2111. Min Act: -0.0000

Data Index: 678226 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2205. Min Act: -0.0000

Data Index: 445480 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1114583 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2176. Min Act: 0.0001

Data Index: 1378223 (Python Code)

Max Activating Token Index: 1003

Text #9

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1964. Min Act: -0.0000

Data Index: 496140 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1200903 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1967. Min Act: -0.0000

Data Index: 771792 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.2048. Min Act: -0.0000

Data Index: 706306 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1716. Min Act: -0.0000

Data Index: 161271 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1054200 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1844. Min Act: -0.0000

Data Index: 624041 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1744. Min Act: -0.0000

Data Index: 555057 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1002395 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1932. Min Act: -0.0000

Data Index: 163955 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.2835. Min Range: -0.2835

Max Act: 0.1688. Min Act: -0.0000

Data Index: 813192 (C4 (Web Text))

Max Activating Token Index: 1014