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

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

Neuron 4772 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: 1.0512. Min Range: -1.0512

Max Act: 1.0512. Min Act: -0.0000

Data Index: 1157421 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 1.0512. Min Range: -1.0512

Max Act: 1.0410. Min Act: -0.0000

Data Index: 880329 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.8380. Min Act: -0.0000

Data Index: 764066 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.9473. Min Act: -0.0000

Data Index: 856792 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1263028 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.9037. Min Act: -0.0000

Data Index: 264300 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.8887. Min Act: -0.0000

Data Index: 88356 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.8743. Min Act: -0.0000

Data Index: 106454 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.8301. Min Act: -0.0000

Data Index: 131799 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1257147 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.8218. Min Act: -0.0000

Data Index: 548055 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.7700. Min Act: -0.0000

Data Index: 475815 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1046028 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.7220. Min Act: -0.0000

Data Index: 609964 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.8242. Min Act: -0.0000

Data Index: 364538 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.6986. Min Act: -0.0000

Data Index: 329698 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1172496 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1057368 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.7408. Min Act: -0.0000

Data Index: 951776 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 1.0512. Min Range: -1.0512

Max Act: 0.7360. Min Act: -0.0000

Data Index: 534898 (C4 (Web Text))

Max Activating Token Index: 156