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

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

Neuron 1611 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9024. Min Range: -2.9024

Max Act: 2.9024. Min Act: -0.0000

Data Index: 1068615 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 2.9024. Min Range: -2.9024

Max Act: 2.4613. Min Act: -0.0000

Data Index: 466810 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.7980. Min Act: -0.0000

Data Index: 536410 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 2.9024. Min Range: -2.9024

Max Act: 2.0742. Min Act: -0.0000

Data Index: 280600 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.7183. Min Act: -0.0000

Data Index: 397275 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.7058. Min Act: -0.0000

Data Index: 1119480 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.6649. Min Act: -0.0000

Data Index: 730548 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.5555. Min Act: -0.0000

Data Index: 1222553 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.6409. Min Act: -0.0000

Data Index: 882605 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.4528. Min Act: -0.0000

Data Index: 1210163 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.5190. Min Act: -0.0000

Data Index: 580923 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.4891. Min Act: -0.0000

Data Index: 146602 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.3881. Min Act: -0.0000

Data Index: 906357 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.5338. Min Act: -0.0000

Data Index: 393475 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1130310 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.5317. Min Act: -0.0000

Data Index: 1303762 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.4411. Min Act: -0.0000

Data Index: 336171 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.4222. Min Act: -0.0000

Data Index: 898892 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.3879. Min Act: -0.0000

Data Index: 435550 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 2.9024. Min Range: -2.9024

Max Act: 1.2955. Min Act: -0.0000

Data Index: 1348085 (C4 (Web Text))

Max Activating Token Index: 521