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

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

Neuron 5370 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: 4.2756. Min Range: -4.2756

Max Act: 4.1609. Min Act: -0.0001

Data Index: 46176 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 4.2756. Min Range: -4.2756

Max Act: 4.2756. Min Act: -0.0000

Data Index: 802180 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 4.2756. Min Range: -4.2756

Max Act: 3.4616. Min Act: -0.0000

Data Index: 1359676 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 4.2756. Min Range: -4.2756

Max Act: 4.1123. Min Act: -0.0001

Data Index: 771745 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 4.2756. Min Range: -4.2756

Max Act: 3.3996. Min Act: -0.0001

Data Index: 716234 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 4.2756. Min Range: -4.2756

Max Act: 3.3504. Min Act: -0.0000

Data Index: 791564 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 4.2756. Min Range: -4.2756

Max Act: 3.4513. Min Act: -0.0000

Data Index: 441925 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 4.2756. Min Range: -4.2756

Max Act: 3.3165. Min Act: -0.0000

Data Index: 608744 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 4.2756. Min Range: -4.2756

Max Act: 3.2097. Min Act: -0.0000

Data Index: 469707 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 4.2756. Min Range: -4.2756

Max Act: 3.3472. Min Act: -0.0001

Data Index: 912684 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 4.2756. Min Range: -4.2756

Max Act: 2.7728. Min Act: -0.0000

Data Index: 769416 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 4.2756. Min Range: -4.2756

Max Act: 3.0918. Min Act: -0.0001

Data Index: 433607 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 4.2756. Min Range: -4.2756

Max Act: 2.4303. Min Act: -0.0001

Data Index: 360277 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 4.2756. Min Range: -4.2756

Max Act: 3.0040. Min Act: -0.0000

Data Index: 227454 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 4.2756. Min Range: -4.2756

Max Act: 2.9660. Min Act: -0.0001

Data Index: 758843 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 4.2756. Min Range: -4.2756

Max Act: 2.9426. Min Act: -0.0001

Data Index: 1107536 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 4.2756. Min Range: -4.2756

Max Act: 2.9263. Min Act: -0.0001

Data Index: 440083 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 4.2756. Min Range: -4.2756

Max Act: 3.0402. Min Act: -0.0001

Data Index: 281247 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 4.2756. Min Range: -4.2756

Max Act: 2.7396. Min Act: -0.0000

Data Index: 1256639 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 4.2756. Min Range: -4.2756

Max Act: 2.8104. Min Act: -0.0001

Data Index: 1073584 (C4 (Web Text))

Max Activating Token Index: 261