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

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

Neuron 2684 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: 1.5106. Min Range: -1.5106

Max Act: 1.5106. Min Act: -0.0001

Data Index: 965761 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.4926. Min Act: -0.0001

Data Index: 642794 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.2583. Min Act: -0.0001

Data Index: 413160 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.2135. Min Act: -0.0001

Data Index: 158399 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.2341. Min Act: -0.0001

Data Index: 849462 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1997. Min Act: -0.0001

Data Index: 313638 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1935. Min Act: -0.0001

Data Index: 1260114 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1607. Min Act: -0.0001

Data Index: 561612 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1447. Min Act: -0.0001

Data Index: 362007 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1242. Min Act: -0.0001

Data Index: 674147 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1553. Min Act: -0.0001

Data Index: 704410 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1021. Min Act: -0.0001

Data Index: 908892 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0555. Min Act: -0.0001

Data Index: 1267390 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1218. Min Act: -0.0001

Data Index: 1323848 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1359. Min Act: -0.0001

Data Index: 187065 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1178. Min Act: -0.0001

Data Index: 784404 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0762. Min Act: -0.0001

Data Index: 70638 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0384. Min Act: -0.0001

Data Index: 1046903 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0341. Min Act: -0.0001

Data Index: 1270442 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0656. Min Act: -0.0001

Data Index: 51934 (C4 (Web Text))

Max Activating Token Index: 680