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

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

Neuron 3778 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6687. Min Act: -0.0000

Data Index: 174299 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6873. Min Act: -0.0001

Data Index: 515704 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6468. Min Act: -0.0001

Data Index: 1346909 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6167. Min Act: -0.0000

Data Index: 441003 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1207642 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6335. Min Act: -0.0001

Data Index: 1249763 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1353409 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1178795 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5223. Min Act: -0.0000

Data Index: 750630 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1096081 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5449. Min Act: -0.0000

Data Index: 971146 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5496. Min Act: -0.0001

Data Index: 506688 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5799. Min Act: -0.0001

Data Index: 155264 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5887. Min Act: -0.0000

Data Index: 56585 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1094433 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5145. Min Act: -0.0001

Data Index: 1261676 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5089. Min Act: -0.0001

Data Index: 912567 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5084. Min Act: -0.0000

Data Index: 483139 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.4743. Min Act: -0.0000

Data Index: 49555 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5198. Min Act: -0.0001

Data Index: 19482 (C4 (Web Text))

Max Activating Token Index: 547