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

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

Neuron 3517 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1499040 (Python Code)

Max Activating Token Index: 137

Text #1

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0799. Min Act: -0.0000

Data Index: 172024 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0996. Min Act: -0.0000

Data Index: 906244 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0988. Min Act: -0.0000

Data Index: 521483 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1188347 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0815. Min Act: -0.0000

Data Index: 580734 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0855. Min Act: -0.0000

Data Index: 345283 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0772. Min Act: -0.0000

Data Index: 153665 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0803. Min Act: -0.0000

Data Index: 388390 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0889. Min Act: -0.0000

Data Index: 585100 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1298358 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0736. Min Act: -0.0000

Data Index: 698002 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0753. Min Act: -0.0000

Data Index: 1581272 (Python Code)

Max Activating Token Index: 785

Text #13

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0708. Min Act: -0.0000

Data Index: 652198 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1226209 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1089484 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0729. Min Act: -0.0000

Data Index: 624988 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0695. Min Act: -0.0000

Data Index: 376162 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0712. Min Act: -0.0000

Data Index: 258421 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0707. Min Act: -0.0000

Data Index: 179944 (C4 (Web Text))

Max Activating Token Index: 331