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

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

Neuron 5097 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: 0.7818. Min Range: -0.7818

Max Act: 0.7818. Min Act: -0.0003

Data Index: 560895 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6416. Min Act: -0.0002

Data Index: 544192 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5862. Min Act: -0.0002

Data Index: 384684 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5824. Min Act: -0.0003

Data Index: 1263658 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5329. Min Act: -0.0003

Data Index: 178590 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5236. Min Act: -0.0003

Data Index: 609249 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5095. Min Act: -0.0002

Data Index: 764530 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5081. Min Act: -0.0002

Data Index: 36648 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5059. Min Act: -0.0002

Data Index: 360111 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.4845. Min Act: -0.0002

Data Index: 1289637 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5034. Min Act: -0.0003

Data Index: 243724 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5157. Min Act: -0.0003

Data Index: 920662 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.4602. Min Act: -0.0003

Data Index: 1264663 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.4684. Min Act: -0.0003

Data Index: 728286 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5039. Min Act: -0.0003

Data Index: 1283061 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.4874. Min Act: -0.0003

Data Index: 271198 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.4761. Min Act: -0.0003

Data Index: 1338503 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.4913. Min Act: -0.0003

Data Index: 1345020 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.4889. Min Act: -0.0002

Data Index: 1166157 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.4533. Min Act: -0.0003

Data Index: 371604 (C4 (Web Text))

Max Activating Token Index: 461