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

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

Neuron 3282 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.6950. Min Act: -0.0001

Data Index: 400039 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.2947. Min Act: -0.0000

Data Index: 1191929 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.0289. Min Act: -0.0001

Data Index: 1299922 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.0626. Min Act: -0.0001

Data Index: 683122 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.0435. Min Act: -0.0001

Data Index: 179202 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.8998. Min Act: -0.0001

Data Index: 1348504 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.0009. Min Act: -0.0001

Data Index: 171002 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.7550. Min Act: -0.0001

Data Index: 996553 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.8624. Min Act: -0.0001

Data Index: 1207732 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.7818. Min Act: -0.0001

Data Index: 428243 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 3.6950. Min Range: -3.6950

Max Act: 3.0021. Min Act: -0.0001

Data Index: 405436 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.8415. Min Act: -0.0001

Data Index: 910485 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.9722. Min Act: -0.0001

Data Index: 961905 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.8121. Min Act: -0.0001

Data Index: 1333450 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.9242. Min Act: -0.0001

Data Index: 631231 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.8004. Min Act: -0.0001

Data Index: 973634 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.6881. Min Act: -0.0001

Data Index: 498350 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.9014. Min Act: -0.0001

Data Index: 860518 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.7332. Min Act: -0.0001

Data Index: 1193011 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 3.6950. Min Range: -3.6950

Max Act: 2.5512. Min Act: -0.0001

Data Index: 429618 (C4 (Web Text))

Max Activating Token Index: 477