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

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

Neuron 4193 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3220. Min Range: -1.3220

Max Act: 1.3220. Min Act: -0.0000

Data Index: 65617 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 1.3220. Min Range: -1.3220

Max Act: 1.1328. Min Act: -0.0000

Data Index: 997568 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 1.3220. Min Range: -1.3220

Max Act: 1.2146. Min Act: -0.0000

Data Index: 740156 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1309769 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.8538. Min Act: -0.0000

Data Index: 316730 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.8298. Min Act: -0.0000

Data Index: 469694 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1165395 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.8047. Min Act: -0.0000

Data Index: 973588 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.7865. Min Act: -0.0000

Data Index: 989007 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.7510. Min Act: -0.0000

Data Index: 671679 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1220470 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1085848 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.7533. Min Act: -0.0000

Data Index: 599466 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.7665. Min Act: -0.0000

Data Index: 979612 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.7450. Min Act: -0.0000

Data Index: 1164655 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.6569. Min Act: -0.0000

Data Index: 37809 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.7391. Min Act: -0.0000

Data Index: 180441 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1332816 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1075141 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 1.3220. Min Range: -1.3220

Max Act: 0.7909. Min Act: -0.0000

Data Index: 87954 (C4 (Web Text))

Max Activating Token Index: 809