Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2986 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.7342. Min Act: -0.0000

Data Index: 1227899 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.9621. Min Act: -0.0000

Data Index: 84507 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.5175. Min Act: -0.0000

Data Index: 1271607 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.6974. Min Act: -0.0000

Data Index: 979869 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.5144. Min Act: -0.0000

Data Index: 745595 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.4631. Min Act: -0.0000

Data Index: 88925 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.4372. Min Act: -0.0000

Data Index: 452927 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.5321. Min Act: -0.0000

Data Index: 480528 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.2904. Min Act: -0.0000

Data Index: 29395 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.1546. Min Act: -0.0000

Data Index: 402606 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.0589. Min Act: -0.0000

Data Index: 211840 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.1478. Min Act: -0.0000

Data Index: 701258 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 3.9621. Min Range: -3.9621

Max Act: 2.9862. Min Act: -0.0000

Data Index: 44328 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 3.9621. Min Range: -3.9621

Max Act: 2.6575. Min Act: -0.0000

Data Index: 1215424 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 3.9621. Min Range: -3.9621

Max Act: 2.7847. Min Act: -0.0000

Data Index: 567603 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 3.9621. Min Range: -3.9621

Max Act: 2.8987. Min Act: -0.0000

Data Index: 551321 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 3.9621. Min Range: -3.9621

Max Act: 2.8902. Min Act: -0.0000

Data Index: 534192 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 3.9621. Min Range: -3.9621

Max Act: 2.9576. Min Act: -0.0000

Data Index: 35696 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 3.9621. Min Range: -3.9621

Max Act: 2.8623. Min Act: -0.0000

Data Index: 1068615 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 3.9621. Min Range: -3.9621

Max Act: 3.0663. Min Act: -0.0000

Data Index: 905380 (C4 (Web Text))

Max Activating Token Index: 241