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

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

Neuron 4799 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.7288. Min Act: -0.0000

Data Index: 155312 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1178142 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.6686. Min Act: -0.0000

Data Index: 457805 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.6446. Min Act: -0.0000

Data Index: 128272 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.6352. Min Act: -0.0001

Data Index: 782806 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1188421 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1032038 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5707. Min Act: -0.0000

Data Index: 849445 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1069400 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5453. Min Act: -0.0000

Data Index: 398491 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5328. Min Act: -0.0001

Data Index: 528505 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1340839 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5167. Min Act: -0.0000

Data Index: 898278 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.4805. Min Act: -0.0000

Data Index: 665777 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1174950 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1173695 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1270468 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1298698 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5196. Min Act: -0.0000

Data Index: 623853 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.4974. Min Act: -0.0000

Data Index: 1273718 (C4 (Web Text))

Max Activating Token Index: 9