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

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

Neuron 1738 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.3710. Min Act: -0.0001

Data Index: 465286 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.3011. Min Act: -0.0001

Data Index: 968494 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1723. Min Act: -0.0001

Data Index: 1310622 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.9678. Min Act: -0.0001

Data Index: 221731 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0256. Min Act: -0.0001

Data Index: 210105 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0256. Min Act: -0.0001

Data Index: 1160125 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.9911. Min Act: -0.0001

Data Index: 37467 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.8241. Min Act: -0.0001

Data Index: 1337887 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.8945. Min Act: -0.0001

Data Index: 828517 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.8414. Min Act: -0.0001

Data Index: 192443 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.7279. Min Act: -0.0001

Data Index: 1022674 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.7993. Min Act: -0.0001

Data Index: 1289070 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.8288. Min Act: -0.0001

Data Index: 1049244 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.7658. Min Act: -0.0001

Data Index: 462181 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.8084. Min Act: -0.0001

Data Index: 449717 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.7806. Min Act: -0.0001

Data Index: 77267 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.7795. Min Act: -0.0001

Data Index: 747029 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.7411. Min Act: -0.0001

Data Index: 1355239 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.7436. Min Act: -0.0001

Data Index: 1352602 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.7398. Min Act: -0.0001

Data Index: 1075228 (C4 (Web Text))

Max Activating Token Index: 707