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

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

Neuron 3170 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.6064. Min Act: -0.0001

Data Index: 536084 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.3623. Min Act: -0.0001

Data Index: 1310745 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.2226. Min Act: -0.0002

Data Index: 254373 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.2835. Min Act: -0.0001

Data Index: 1298595 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.2686. Min Act: -0.0001

Data Index: 1038350 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.2708. Min Act: -0.0002

Data Index: 606553 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.2056. Min Act: -0.0001

Data Index: 816978 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.1951. Min Act: -0.0002

Data Index: 522827 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.2011. Min Act: -0.0001

Data Index: 447587 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.1835. Min Act: -0.0001

Data Index: 151958 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.1921. Min Act: -0.0001

Data Index: 1260521 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.1590. Min Act: -0.0002

Data Index: 893086 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.1723. Min Act: -0.0002

Data Index: 575882 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.1013. Min Act: -0.0002

Data Index: 1015602 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.1488. Min Act: -0.0002

Data Index: 338106 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.0936. Min Act: -0.0002

Data Index: 131740 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.0382. Min Act: -0.0002

Data Index: 1100599 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.1334. Min Act: -0.0002

Data Index: 148204 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.1910. Min Act: -0.0002

Data Index: 473014 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.6064. Min Range: -1.6064

Max Act: 1.0395. Min Act: -0.0001

Data Index: 97723 (C4 (Web Text))

Max Activating Token Index: 652