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

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

Neuron 1452 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1358. Min Range: -3.1358

Max Act: 3.1358. Min Act: -0.0000

Data Index: 1243908 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.7621. Min Act: -0.0000

Data Index: 1024380 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.7481. Min Act: -0.0000

Data Index: 1092154 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.6965. Min Act: -0.0000

Data Index: 246563 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.6047. Min Act: -0.0000

Data Index: 195163 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.5582. Min Act: -0.0000

Data Index: 717295 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.2788. Min Act: -0.0000

Data Index: 375787 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.5932. Min Act: -0.0000

Data Index: 290903 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.3202. Min Act: -0.0000

Data Index: 690957 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.2117. Min Act: -0.0000

Data Index: 1288652 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.1194. Min Act: -0.0000

Data Index: 1230138 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.2046. Min Act: -0.0000

Data Index: 833953 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.0935. Min Act: -0.0000

Data Index: 1058548 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.1807. Min Act: -0.0000

Data Index: 1325091 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.0510. Min Act: -0.0000

Data Index: 973113 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.0303. Min Act: -0.0000

Data Index: 346531 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.2356. Min Act: -0.0000

Data Index: 565343 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.1358. Min Range: -3.1358

Max Act: 1.8794. Min Act: -0.0000

Data Index: 360466 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 3.1358. Min Range: -3.1358

Max Act: 2.0872. Min Act: -0.0000

Data Index: 982014 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 3.1358. Min Range: -3.1358

Max Act: 1.9725. Min Act: -0.0000

Data Index: 321157 (C4 (Web Text))

Max Activating Token Index: 190