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

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

Neuron 3071 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.9745. Min Act: -0.0000

Data Index: 809853 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8729. Min Act: -0.0000

Data Index: 968980 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1140621 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7738. Min Act: -0.0000

Data Index: 328368 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7638. Min Act: -0.0000

Data Index: 171858 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1262798 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.6958. Min Act: -0.0000

Data Index: 842471 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7288. Min Act: -0.0000

Data Index: 959023 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1210446 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7446. Min Act: -0.0000

Data Index: 225506 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7098. Min Act: -0.0000

Data Index: 531930 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7398. Min Act: -0.0000

Data Index: 169307 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7100. Min Act: -0.0000

Data Index: 61579 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7311. Min Act: -0.0000

Data Index: 444311 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.6770. Min Act: -0.0000

Data Index: 453380 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7243. Min Act: -0.0000

Data Index: 821625 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1171281 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7225. Min Act: -0.0000

Data Index: 163852 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7127. Min Act: -0.0000

Data Index: 200768 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7145. Min Act: -0.0000

Data Index: 783751 (C4 (Web Text))

Max Activating Token Index: 276