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

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

Neuron 5278 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: 0.6004. Min Range: -0.6004

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1185763 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.5608. Min Act: 0.0000

Data Index: 913989 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.5334. Min Act: -0.0000

Data Index: 713443 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1264505 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.5110. Min Act: -0.0000

Data Index: 8639 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1101186 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.5052. Min Act: -0.0000

Data Index: 609105 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4863. Min Act: -0.0000

Data Index: 226383 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1198737 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4597. Min Act: -0.0000

Data Index: 703526 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1031007 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4568. Min Act: -0.0000

Data Index: 865412 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4360. Min Act: -0.0000

Data Index: 303144 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1064916 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4405. Min Act: -0.0000

Data Index: 884133 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1028138 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4269. Min Act: -0.0000

Data Index: 453053 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4292. Min Act: -0.0000

Data Index: 751415 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1296419 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1258479 (C4 (Web Text))

Max Activating Token Index: 238