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

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

Neuron 4039 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8857. Min Act: -0.0002

Data Index: 272985 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9248. Min Act: -0.0002

Data Index: 64476 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9349. Min Act: -0.0002

Data Index: 959643 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9404. Min Act: -0.0002

Data Index: 815479 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9948. Min Act: -0.0002

Data Index: 880548 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.7023. Min Act: -0.0002

Data Index: 1290842 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8183. Min Act: -0.0002

Data Index: 430200 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8076. Min Act: -0.0002

Data Index: 410226 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9332. Min Act: -0.0002

Data Index: 4910 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8812. Min Act: -0.0002

Data Index: 483218 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9074. Min Act: -0.0002

Data Index: 256933 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9641. Min Act: -0.0002

Data Index: 499646 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9010. Min Act: -0.0002

Data Index: 102594 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8639. Min Act: -0.0002

Data Index: 64392 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.7849. Min Act: -0.0002

Data Index: 23173 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 1.0141. Min Range: -1.0141

Max Act: 1.0141. Min Act: -0.0002

Data Index: 220536 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8809. Min Act: -0.0002

Data Index: 149995 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8695. Min Act: -0.0002

Data Index: 471504 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8208. Min Act: -0.0002

Data Index: 1059340 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8928. Min Act: -0.0002

Data Index: 897692 (C4 (Web Text))

Max Activating Token Index: 948