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

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

Neuron 957 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1115861 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.5619. Min Act: -0.0000

Data Index: 264017 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.5281. Min Act: -0.0000

Data Index: 685451 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.5543. Min Act: -0.0000

Data Index: 882446 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4617. Min Act: -0.0000

Data Index: 72684 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4954. Min Act: -0.0000

Data Index: 733491 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1031958 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4588. Min Act: -0.0000

Data Index: 466265 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1088045 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4646. Min Act: 0.0000

Data Index: 1253840 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4767. Min Act: -0.0000

Data Index: 102234 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4436. Min Act: -0.0000

Data Index: 474631 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4321. Min Act: -0.0000

Data Index: 437420 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4254. Min Act: -0.0000

Data Index: 643239 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4123. Min Act: -0.0000

Data Index: 167137 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4366. Min Act: -0.0000

Data Index: 690568 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.3988. Min Act: -0.0000

Data Index: 751181 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.4085. Min Act: -0.0000

Data Index: 643188 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.3939. Min Act: -0.0000

Data Index: 244384 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.6270. Min Range: -0.6270

Max Act: 0.3823. Min Act: -0.0000

Data Index: 1341721 (C4 (Web Text))

Max Activating Token Index: 969