Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2661 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0828. Min Act: -0.0000

Data Index: 303352 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.1285. Min Act: -0.0000

Data Index: 153595 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.1042. Min Act: -0.0000

Data Index: 104444 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0358. Min Act: -0.0000

Data Index: 25683 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0818. Min Act: -0.0000

Data Index: 898007 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0552. Min Act: -0.0000

Data Index: 38265 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9699. Min Act: -0.0000

Data Index: 483500 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1156182 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9607. Min Act: -0.0000

Data Index: 71843 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9841. Min Act: -0.0000

Data Index: 74812 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9284. Min Act: -0.0000

Data Index: 933821 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.8954. Min Act: -0.0000

Data Index: 690309 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9247. Min Act: -0.0000

Data Index: 310550 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1166143 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9337. Min Act: -0.0000

Data Index: 1287244 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1181256 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.8640. Min Act: -0.0000

Data Index: 697126 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.8853. Min Act: -0.0000

Data Index: 20578 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0042. Min Act: -0.0000

Data Index: 862428 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.8490. Min Act: -0.0000

Data Index: 721667 (C4 (Web Text))

Max Activating Token Index: 719