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

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

Neuron 4993 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5551. Min Range: -2.5551

Max Act: 2.5551. Min Act: -0.0000

Data Index: 1252543 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 2.5551. Min Range: -2.5551

Max Act: 2.3255. Min Act: -0.0000

Data Index: 1332021 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 2.5551. Min Range: -2.5551

Max Act: 2.2017. Min Act: -0.0000

Data Index: 520600 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 2.5551. Min Range: -2.5551

Max Act: 2.1772. Min Act: -0.0000

Data Index: 242406 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 2.5551. Min Range: -2.5551

Max Act: 2.0192. Min Act: -0.0000

Data Index: 1080971 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 2.5551. Min Range: -2.5551

Max Act: 1.9836. Min Act: -0.0000

Data Index: 344891 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 2.5551. Min Range: -2.5551

Max Act: 1.8775. Min Act: -0.0000

Data Index: 957640 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 2.5551. Min Range: -2.5551

Max Act: 2.0605. Min Act: -0.0000

Data Index: 1226701 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 2.5551. Min Range: -2.5551

Max Act: 2.0379. Min Act: -0.0000

Data Index: 811257 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 2.5551. Min Range: -2.5551

Max Act: 2.0246. Min Act: -0.0000

Data Index: 1129341 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 2.5551. Min Range: -2.5551

Max Act: 2.0204. Min Act: -0.0000

Data Index: 1313932 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 2.5551. Min Range: -2.5551

Max Act: 1.9603. Min Act: -0.0000

Data Index: 1016131 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 2.5551. Min Range: -2.5551

Max Act: 2.0296. Min Act: -0.0000

Data Index: 76570 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 2.5551. Min Range: -2.5551

Max Act: 1.7996. Min Act: -0.0000

Data Index: 128945 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 2.5551. Min Range: -2.5551

Max Act: 1.8970. Min Act: -0.0000

Data Index: 212134 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 2.5551. Min Range: -2.5551

Max Act: 1.8781. Min Act: -0.0000

Data Index: 1247474 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 2.5551. Min Range: -2.5551

Max Act: 1.8538. Min Act: -0.0000

Data Index: 234638 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 2.5551. Min Range: -2.5551

Max Act: 1.8251. Min Act: -0.0000

Data Index: 301522 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 2.5551. Min Range: -2.5551

Max Act: 1.8068. Min Act: -0.0000

Data Index: 612430 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 2.5551. Min Range: -2.5551

Max Act: 1.9097. Min Act: -0.0000

Data Index: 1178690 (C4 (Web Text))

Max Activating Token Index: 334