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

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

Neuron 2561 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.9433. Min Act: -0.0000

Data Index: 275119 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.0787. Min Range: -3.0787

Max Act: 3.0787. Min Act: -0.0000

Data Index: 730072 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.8047. Min Act: -0.0000

Data Index: 988892 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.6194. Min Act: -0.0000

Data Index: 221082 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.5062. Min Act: -0.0000

Data Index: 92683 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.4084. Min Act: -0.0000

Data Index: 94179 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.2435. Min Act: -0.0000

Data Index: 1077248 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.3065. Min Act: -0.0000

Data Index: 509017 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.0213. Min Act: -0.0000

Data Index: 873840 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.2072. Min Act: -0.0000

Data Index: 555430 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.1709. Min Act: -0.0000

Data Index: 742035 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.1683. Min Act: -0.0000

Data Index: 350807 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.0218. Min Act: -0.0000

Data Index: 88000 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 3.0787. Min Range: -3.0787

Max Act: 1.9923. Min Act: -0.0000

Data Index: 162663 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.2071. Min Act: -0.0000

Data Index: 570125 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.0621. Min Act: -0.0000

Data Index: 355628 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.0301. Min Act: -0.0000

Data Index: 170193 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 3.0787. Min Range: -3.0787

Max Act: 1.9625. Min Act: -0.0000

Data Index: 254689 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 3.0787. Min Range: -3.0787

Max Act: 2.0547. Min Act: -0.0000

Data Index: 451565 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 3.0787. Min Range: -3.0787

Max Act: 1.9433. Min Act: -0.0000

Data Index: 217524 (C4 (Web Text))

Max Activating Token Index: 60