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

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

Neuron 2597 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: 2.6621. Min Range: -2.6621

Max Act: 2.6621. Min Act: -0.0000

Data Index: 490792 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 2.6621. Min Range: -2.6621

Max Act: 2.0598. Min Act: -0.0000

Data Index: 890899 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.9336. Min Act: -0.0000

Data Index: 567026 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.8915. Min Act: -0.0000

Data Index: 1170004 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.8597. Min Act: -0.0000

Data Index: 164660 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.7047. Min Act: -0.0000

Data Index: 1186235 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.7079. Min Act: -0.0000

Data Index: 1238353 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.7909. Min Act: -0.0000

Data Index: 577665 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.5717. Min Act: -0.0000

Data Index: 1330151 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.4937. Min Act: -0.0000

Data Index: 404241 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.3719. Min Act: -0.0000

Data Index: 784105 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.4394. Min Act: -0.0000

Data Index: 257818 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.4931. Min Act: -0.0000

Data Index: 11896 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.3747. Min Act: -0.0000

Data Index: 1098260 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.4406. Min Act: -0.0000

Data Index: 697043 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.4371. Min Act: -0.0000

Data Index: 461787 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.3771. Min Act: -0.0000

Data Index: 755971 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.4656. Min Act: -0.0000

Data Index: 300857 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.3785. Min Act: -0.0000

Data Index: 1178028 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 2.6621. Min Range: -2.6621

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1642725 (Python Code)

Max Activating Token Index: 266