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

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

Neuron 3087 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.7634. Min Act: -0.0001

Data Index: 682557 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.9220. Min Act: -0.0001

Data Index: 503690 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.8697. Min Act: -0.0001

Data Index: 1289958 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.7762. Min Act: -0.0001

Data Index: 637081 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.6219. Min Act: -0.0001

Data Index: 1109907 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.6563. Min Act: -0.0001

Data Index: 1616778 (Python Code)

Max Activating Token Index: 149

Text #6

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.6173. Min Act: -0.0001

Data Index: 1103762 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.6266. Min Act: -0.0001

Data Index: 1209389 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.5593. Min Act: -0.0001

Data Index: 1205678 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.6330. Min Act: -0.0001

Data Index: 710154 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.6413. Min Act: -0.0001

Data Index: 1382097 (Python Code)

Max Activating Token Index: 396

Text #11

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.5727. Min Act: -0.0001

Data Index: 682116 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.5863. Min Act: -0.0001

Data Index: 122831 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.5723. Min Act: -0.0001

Data Index: 647189 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.5702. Min Act: -0.0001

Data Index: 835065 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.5674. Min Act: -0.0001

Data Index: 902278 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.5056. Min Act: -0.0001

Data Index: 1339089 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.6379. Min Act: -0.0001

Data Index: 1285687 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.6085. Min Act: -0.0001

Data Index: 531075 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.6265. Min Act: -0.0001

Data Index: 665188 (C4 (Web Text))

Max Activating Token Index: 23