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

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

Neuron 2874 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.8112. Min Act: -0.0003

Data Index: 924304 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.7451. Min Act: -0.0002

Data Index: 25199 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6782. Min Act: -0.0003

Data Index: 927213 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6703. Min Act: -0.0003

Data Index: 935376 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6429. Min Act: -0.0002

Data Index: 991387 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6176. Min Act: -0.0002

Data Index: 1331606 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6263. Min Act: -0.0003

Data Index: 27305 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6225. Min Act: -0.0003

Data Index: 135404 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6021. Min Act: -0.0003

Data Index: 1181974 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6006. Min Act: -0.0003

Data Index: 1143617 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6831. Min Act: -0.0002

Data Index: 51559 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6101. Min Act: -0.0002

Data Index: 143546 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6113. Min Act: -0.0003

Data Index: 566083 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5898. Min Act: -0.0002

Data Index: 589438 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5869. Min Act: -0.0002

Data Index: 324697 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5671. Min Act: -0.0002

Data Index: 802490 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5646. Min Act: -0.0003

Data Index: 1141499 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5630. Min Act: -0.0003

Data Index: 1055480 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5988. Min Act: -0.0002

Data Index: 442360 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5783. Min Act: -0.0003

Data Index: 552826 (C4 (Web Text))

Max Activating Token Index: 74