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

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

Neuron 657 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0507. Min Range: -1.0507

Max Act: 1.0507. Min Act: -0.0000

Data Index: 991881 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.0507. Min Range: -1.0507

Max Act: 1.0199. Min Act: -0.0000

Data Index: 241572 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1097743 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9142. Min Act: -0.0000

Data Index: 126902 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8623. Min Act: -0.0000

Data Index: 636003 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9407. Min Act: -0.0000

Data Index: 519728 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9189. Min Act: -0.0000

Data Index: 77488 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9272. Min Act: -0.0000

Data Index: 804130 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8714. Min Act: -0.0000

Data Index: 446104 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8985. Min Act: -0.0000

Data Index: 457040 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9907. Min Act: -0.0000

Data Index: 663919 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8698. Min Act: -0.0000

Data Index: 139069 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1251234 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8530. Min Act: -0.0000

Data Index: 657404 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1153207 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8538. Min Act: -0.0000

Data Index: 559874 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1222853 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8734. Min Act: -0.0000

Data Index: 479288 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8251. Min Act: -0.0000

Data Index: 720839 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8261. Min Act: -0.0000

Data Index: 153790 (C4 (Web Text))

Max Activating Token Index: 611