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

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

Neuron 4410 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: 0.8441. Min Range: -0.8441

Max Act: 0.8441. Min Act: -0.0001

Data Index: 116537 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.8076. Min Act: -0.0001

Data Index: 485675 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7535. Min Act: -0.0001

Data Index: 301914 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7279. Min Act: -0.0001

Data Index: 611116 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7814. Min Act: -0.0001

Data Index: 533545 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6959. Min Act: -0.0001

Data Index: 891580 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6794. Min Act: -0.0001

Data Index: 225103 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6684. Min Act: -0.0001

Data Index: 309034 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6555. Min Act: -0.0001

Data Index: 548879 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7202. Min Act: -0.0001

Data Index: 420873 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6690. Min Act: -0.0001

Data Index: 924493 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7023. Min Act: -0.0001

Data Index: 1315844 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5992. Min Act: -0.0001

Data Index: 1223817 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6993. Min Act: -0.0001

Data Index: 272137 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6588. Min Act: -0.0001

Data Index: 145160 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6878. Min Act: -0.0001

Data Index: 394244 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7024. Min Act: -0.0001

Data Index: 1029870 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6771. Min Act: -0.0001

Data Index: 438237 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7159. Min Act: -0.0001

Data Index: 45273 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6800. Min Act: -0.0001

Data Index: 1003188 (C4 (Web Text))

Max Activating Token Index: 192