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

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

Neuron 3900 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4734. Min Range: -1.4734

Max Act: 1.4734. Min Act: -0.0000

Data Index: 558416 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.4734. Min Range: -1.4734

Max Act: 1.0923. Min Act: -0.0000

Data Index: 593938 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 1.4734. Min Range: -1.4734

Max Act: 1.0000. Min Act: -0.0000

Data Index: 915013 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 1.4734. Min Range: -1.4734

Max Act: 1.0009. Min Act: -0.0000

Data Index: 195823 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.9941. Min Act: -0.0000

Data Index: 724747 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1169057 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.9346. Min Act: -0.0000

Data Index: 510925 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1144005 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1239165 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1300141 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.8730. Min Act: -0.0000

Data Index: 610615 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.8610. Min Act: -0.0000

Data Index: 494419 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.8524. Min Act: -0.0000

Data Index: 390688 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1183427 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.7176. Min Act: -0.0000

Data Index: 841709 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.7641. Min Act: -0.0000

Data Index: 372830 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1083849 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.7669. Min Act: -0.0000

Data Index: 627893 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.7202. Min Act: -0.0000

Data Index: 563400 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 1.4734. Min Range: -1.4734

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1184879 (C4 (Web Text))

Max Activating Token Index: 444