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

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

Neuron 1908 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7944. Min Act: -0.0001

Data Index: 587788 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6597. Min Act: -0.0001

Data Index: 1252905 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6982. Min Act: -0.0001

Data Index: 590699 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6320. Min Act: -0.0001

Data Index: 318767 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6332. Min Act: -0.0001

Data Index: 595144 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5864. Min Act: -0.0001

Data Index: 940803 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5962. Min Act: -0.0001

Data Index: 583921 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5799. Min Act: -0.0001

Data Index: 1158439 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6677. Min Act: -0.0001

Data Index: 142929 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6610. Min Act: -0.0001

Data Index: 1102663 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5647. Min Act: -0.0001

Data Index: 463246 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6108. Min Act: -0.0001

Data Index: 789907 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6277. Min Act: -0.0001

Data Index: 211579 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5869. Min Act: -0.0001

Data Index: 588150 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6990. Min Act: -0.0001

Data Index: 593870 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5582. Min Act: -0.0001

Data Index: 376989 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5542. Min Act: -0.0001

Data Index: 714285 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5229. Min Act: -0.0001

Data Index: 823268 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1281723 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5334. Min Act: -0.0001

Data Index: 153987 (C4 (Web Text))

Max Activating Token Index: 131