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

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

Neuron 5032 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3167. Min Range: -2.3167

Max Act: 2.3167. Min Act: -0.0000

Data Index: 3564 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 2.3167. Min Range: -2.3167

Max Act: 1.2650. Min Act: -0.0000

Data Index: 373969 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 2.3167. Min Range: -2.3167

Max Act: 1.0801. Min Act: -0.0000

Data Index: 262054 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 2.3167. Min Range: -2.3167

Max Act: 1.0368. Min Act: -0.0000

Data Index: 821532 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 2.3167. Min Range: -2.3167

Max Act: 0.9534. Min Act: -0.0000

Data Index: 232005 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 2.3167. Min Range: -2.3167

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1355617 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 2.3167. Min Range: -2.3167

Max Act: 1.0912. Min Act: -0.0000

Data Index: 384844 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 2.3167. Min Range: -2.3167

Max Act: 1.0718. Min Act: -0.0000

Data Index: 1171864 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 2.3167. Min Range: -2.3167

Max Act: 1.1351. Min Act: -0.0000

Data Index: 233486 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 2.3167. Min Range: -2.3167

Max Act: 1.0468. Min Act: -0.0000

Data Index: 301495 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 2.3167. Min Range: -2.3167

Max Act: 1.1045. Min Act: -0.0000

Data Index: 22144 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 2.3167. Min Range: -2.3167

Max Act: 1.0199. Min Act: -0.0000

Data Index: 249471 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 2.3167. Min Range: -2.3167

Max Act: 0.9589. Min Act: -0.0000

Data Index: 472308 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 2.3167. Min Range: -2.3167

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1111198 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 2.3167. Min Range: -2.3167

Max Act: 0.9374. Min Act: -0.0000

Data Index: 929027 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 2.3167. Min Range: -2.3167

Max Act: 0.9197. Min Act: -0.0000

Data Index: 968842 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 2.3167. Min Range: -2.3167

Max Act: 0.9222. Min Act: -0.0000

Data Index: 3257 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 2.3167. Min Range: -2.3167

Max Act: 0.9153. Min Act: -0.0000

Data Index: 186184 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 2.3167. Min Range: -2.3167

Max Act: 0.9155. Min Act: -0.0000

Data Index: 698104 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 2.3167. Min Range: -2.3167

Max Act: 0.9537. Min Act: -0.0000

Data Index: 869955 (C4 (Web Text))

Max Activating Token Index: 603