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

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

Neuron 4027 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: 1.1617. Min Range: -1.1617

Max Act: 1.1617. Min Act: -0.0003

Data Index: 550421 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.1189. Min Act: -0.0002

Data Index: 312341 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0104. Min Act: -0.0003

Data Index: 914999 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0424. Min Act: -0.0002

Data Index: 396619 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0192. Min Act: -0.0003

Data Index: 1344648 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0156. Min Act: -0.0003

Data Index: 901151 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0164. Min Act: -0.0003

Data Index: 315408 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9333. Min Act: -0.0003

Data Index: 757118 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0212. Min Act: -0.0003

Data Index: 124354 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9566. Min Act: -0.0003

Data Index: 1269593 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9829. Min Act: -0.0003

Data Index: 216380 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0149. Min Act: -0.0002

Data Index: 134909 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9278. Min Act: -0.0003

Data Index: 1186991 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9518. Min Act: -0.0003

Data Index: 543246 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9181. Min Act: -0.0003

Data Index: 180133 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.8924. Min Act: -0.0003

Data Index: 744522 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9120. Min Act: -0.0002

Data Index: 946438 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.8933. Min Act: -0.0003

Data Index: 840603 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9315. Min Act: -0.0003

Data Index: 540829 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9572. Min Act: -0.0003

Data Index: 758962 (C4 (Web Text))

Max Activating Token Index: 233