Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3583 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.1580. Min Act: -0.0001

Data Index: 780788 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9865. Min Act: -0.0001

Data Index: 455802 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8949. Min Act: -0.0001

Data Index: 1053259 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9166. Min Act: -0.0001

Data Index: 791576 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9309. Min Act: -0.0001

Data Index: 562268 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8230. Min Act: -0.0001

Data Index: 1288867 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7832. Min Act: -0.0001

Data Index: 232734 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7467. Min Act: -0.0001

Data Index: 1172031 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8659. Min Act: -0.0001

Data Index: 955883 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8150. Min Act: -0.0001

Data Index: 844932 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7518. Min Act: -0.0001

Data Index: 695601 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7725. Min Act: -0.0001

Data Index: 51905 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7397. Min Act: -0.0001

Data Index: 1329585 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7369. Min Act: -0.0001

Data Index: 661552 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7043. Min Act: -0.0001

Data Index: 1059229 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.6696. Min Act: -0.0001

Data Index: 197088 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.6457. Min Act: -0.0001

Data Index: 81475 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.6765. Min Act: -0.0001

Data Index: 729151 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.6542. Min Act: -0.0001

Data Index: 852161 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.6035. Min Act: -0.0001

Data Index: 526558 (C4 (Web Text))

Max Activating Token Index: 694