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

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

Neuron 3088 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: 4.6618. Min Range: -4.6618

Max Act: 4.6618. Min Act: -0.0000

Data Index: 1016101 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 4.6618. Min Range: -4.6618

Max Act: 4.2178. Min Act: -0.0001

Data Index: 183676 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.8262. Min Act: -0.0000

Data Index: 369127 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.9185. Min Act: -0.0000

Data Index: 387593 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.7446. Min Act: -0.0000

Data Index: 727837 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.7125. Min Act: -0.0001

Data Index: 561021 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.7378. Min Act: -0.0000

Data Index: 102745 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.7901. Min Act: -0.0001

Data Index: 610525 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.9084. Min Act: -0.0000

Data Index: 405047 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.5725. Min Act: -0.0001

Data Index: 456387 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.7500. Min Act: -0.0000

Data Index: 558029 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.5684. Min Act: -0.0000

Data Index: 162484 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.5476. Min Act: -0.0000

Data Index: 99569 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.7118. Min Act: -0.0000

Data Index: 128518 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.4061. Min Act: -0.0001

Data Index: 1250900 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.6890. Min Act: -0.0001

Data Index: 1265323 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.3573. Min Act: -0.0000

Data Index: 444746 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.7080. Min Act: -0.0000

Data Index: 1338163 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.4886. Min Act: -0.0000

Data Index: 1152498 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 4.6618. Min Range: -4.6618

Max Act: 3.4886. Min Act: -0.0000

Data Index: 183279 (C4 (Web Text))

Max Activating Token Index: 4