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

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

Neuron 3944 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: 0.8294. Min Range: -0.8294

Max Act: 0.8294. Min Act: -0.0001

Data Index: 753681 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.8293. Min Act: -0.0001

Data Index: 458628 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.8024. Min Act: -0.0000

Data Index: 940534 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1128773 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7575. Min Act: 0.0002

Data Index: 615480 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7235. Min Act: -0.0000

Data Index: 486615 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7144. Min Act: 0.0001

Data Index: 23776 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1327684 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6847. Min Act: 0.0002

Data Index: 520396 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7065. Min Act: -0.0000

Data Index: 463731 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7042. Min Act: -0.0000

Data Index: 978650 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6803. Min Act: -0.0000

Data Index: 205671 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6956. Min Act: -0.0001

Data Index: 364156 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6696. Min Act: -0.0001

Data Index: 809419 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6658. Min Act: -0.0000

Data Index: 766203 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6756. Min Act: 0.0002

Data Index: 521987 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1353827 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1178747 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6652. Min Act: -0.0000

Data Index: 384035 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6612. Min Act: -0.0000

Data Index: 344750 (C4 (Web Text))

Max Activating Token Index: 544