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

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

Neuron 4047 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.5456. Min Act: -0.0000

Data Index: 1167424 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.7331. Min Act: -0.0000

Data Index: 998178 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.6617. Min Act: -0.0000

Data Index: 380045 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.6690. Min Act: -0.0000

Data Index: 716014 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.5651. Min Act: -0.0001

Data Index: 1094915 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.5878. Min Act: -0.0000

Data Index: 125314 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.6389. Min Act: -0.0001

Data Index: 24294 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.5739. Min Act: -0.0000

Data Index: 1277409 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.5445. Min Act: -0.0001

Data Index: 1168167 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.5525. Min Act: -0.0001

Data Index: 1006001 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.5435. Min Act: -0.0000

Data Index: 387185 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.5395. Min Act: -0.0001

Data Index: 420048 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.4240. Min Act: -0.0000

Data Index: 547951 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.5212. Min Act: -0.0000

Data Index: 894604 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.4994. Min Act: -0.0001

Data Index: 818461 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.4883. Min Act: -0.0001

Data Index: 714006 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.4817. Min Act: -0.0000

Data Index: 150060 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.4116. Min Act: -0.0001

Data Index: 966055 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.4198. Min Act: -0.0001

Data Index: 399249 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.4969. Min Act: -0.0000

Data Index: 1212556 (C4 (Web Text))

Max Activating Token Index: 152