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

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

Neuron 4639 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: 5.0890. Min Range: -5.0890

Max Act: 4.9465. Min Act: -0.0000

Data Index: 704965 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 5.0890. Min Range: -5.0890

Max Act: 5.0890. Min Act: -0.0000

Data Index: 272066 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 5.0890. Min Range: -5.0890

Max Act: 4.8354. Min Act: -0.0000

Data Index: 997212 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 5.0890. Min Range: -5.0890

Max Act: 4.3632. Min Act: -0.0000

Data Index: 1171027 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 5.0890. Min Range: -5.0890

Max Act: 4.1390. Min Act: -0.0000

Data Index: 418902 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 5.0890. Min Range: -5.0890

Max Act: 4.1109. Min Act: -0.0000

Data Index: 809922 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 5.0890. Min Range: -5.0890

Max Act: 3.6922. Min Act: -0.0000

Data Index: 752985 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 5.0890. Min Range: -5.0890

Max Act: 3.6678. Min Act: -0.0000

Data Index: 684225 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 5.0890. Min Range: -5.0890

Max Act: 3.5205. Min Act: -0.0000

Data Index: 1336583 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 5.0890. Min Range: -5.0890

Max Act: 3.5059. Min Act: -0.0000

Data Index: 36767 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 5.0890. Min Range: -5.0890

Max Act: 3.5569. Min Act: -0.0000

Data Index: 882745 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 5.0890. Min Range: -5.0890

Max Act: 3.3319. Min Act: -0.0000

Data Index: 1217262 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 5.0890. Min Range: -5.0890

Max Act: 3.3210. Min Act: -0.0000

Data Index: 654958 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 5.0890. Min Range: -5.0890

Max Act: 3.3825. Min Act: -0.0000

Data Index: 1205999 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 5.0890. Min Range: -5.0890

Max Act: 3.2204. Min Act: -0.0000

Data Index: 493105 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 5.0890. Min Range: -5.0890

Max Act: 3.1568. Min Act: -0.0000

Data Index: 803227 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 5.0890. Min Range: -5.0890

Max Act: 2.9116. Min Act: -0.0000

Data Index: 1160634 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 5.0890. Min Range: -5.0890

Max Act: 2.7802. Min Act: -0.0000

Data Index: 780526 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 5.0890. Min Range: -5.0890

Max Act: 3.0564. Min Act: -0.0000

Data Index: 37475 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 5.0890. Min Range: -5.0890

Max Act: 2.9607. Min Act: -0.0000

Data Index: 295724 (C4 (Web Text))

Max Activating Token Index: 828