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

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

Neuron 4017 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6596. Min Range: -2.6596

Max Act: 2.6596. Min Act: -0.0000

Data Index: 349326 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 2.6596. Min Range: -2.6596

Max Act: 2.4075. Min Act: -0.0000

Data Index: 260480 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 2.6596. Min Range: -2.6596

Max Act: 2.3263. Min Act: -0.0000

Data Index: 709897 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.8738. Min Act: -0.0000

Data Index: 539770 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.6585. Min Act: -0.0000

Data Index: 508696 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.4847. Min Act: -0.0000

Data Index: 449324 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.5358. Min Act: -0.0000

Data Index: 727163 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.3797. Min Act: -0.0000

Data Index: 1252466 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.3661. Min Act: -0.0000

Data Index: 528585 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.3440. Min Act: -0.0000

Data Index: 620080 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.3486. Min Act: -0.0000

Data Index: 1228872 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.3520. Min Act: -0.0000

Data Index: 68054 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.3326. Min Act: -0.0000

Data Index: 1122467 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.4037. Min Act: -0.0000

Data Index: 724762 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.4071. Min Act: -0.0000

Data Index: 298829 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.2500. Min Act: -0.0000

Data Index: 304736 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.2489. Min Act: -0.0000

Data Index: 202705 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.1639. Min Act: -0.0000

Data Index: 242800 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1354014 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 2.6596. Min Range: -2.6596

Max Act: 1.2333. Min Act: -0.0000

Data Index: 157760 (C4 (Web Text))

Max Activating Token Index: 231