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

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

Neuron 4623 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0598. Min Range: -1.0598

Max Act: 1.0598. Min Act: -0.0000

Data Index: 560605 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.9512. Min Act: -0.0000

Data Index: 14175 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.9655. Min Act: -0.0000

Data Index: 260695 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1205583 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8277. Min Act: -0.0000

Data Index: 671912 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1323719 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8617. Min Act: -0.0000

Data Index: 726228 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8055. Min Act: -0.0000

Data Index: 991573 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7857. Min Act: -0.0000

Data Index: 802267 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7980. Min Act: -0.0000

Data Index: 713 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1310562 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7433. Min Act: -0.0000

Data Index: 741317 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7577. Min Act: -0.0000

Data Index: 132002 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1153125 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7000. Min Act: -0.0000

Data Index: 85031 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1292177 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1187060 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7606. Min Act: -0.0000

Data Index: 759419 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7127. Min Act: -0.0000

Data Index: 538895 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.7323. Min Act: -0.0000

Data Index: 875756 (C4 (Web Text))

Max Activating Token Index: 299