Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 626 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.9116. Min Act: -0.0000

Data Index: 147996 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7778. Min Act: -0.0000

Data Index: 536585 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7609. Min Act: -0.0000

Data Index: 973097 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7518. Min Act: -0.0000

Data Index: 902968 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.6591. Min Act: -0.0000

Data Index: 1066310 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7325. Min Act: -0.0000

Data Index: 901126 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.6737. Min Act: -0.0000

Data Index: 1207412 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.6751. Min Act: -0.0000

Data Index: 862847 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.5746. Min Act: -0.0000

Data Index: 463258 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.5379. Min Act: -0.0000

Data Index: 976299 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.6313. Min Act: -0.0000

Data Index: 22701 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.5257. Min Act: -0.0000

Data Index: 721880 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.5042. Min Act: -0.0000

Data Index: 120901 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.3603. Min Act: -0.0000

Data Index: 684849 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1064793 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.3402. Min Act: -0.0000

Data Index: 1306350 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.4198. Min Act: -0.0000

Data Index: 227582 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.4897. Min Act: -0.0000

Data Index: 1316135 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.3894. Min Act: -0.0000

Data Index: 1053296 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.3905. Min Act: -0.0000

Data Index: 880976 (C4 (Web Text))

Max Activating Token Index: 57