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

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

Neuron 3950 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: 3.6820. Min Range: -3.6820

Max Act: 3.6820. Min Act: -0.0000

Data Index: 581658 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 3.6820. Min Range: -3.6820

Max Act: 2.7402. Min Act: -0.0000

Data Index: 1023652 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 3.6820. Min Range: -3.6820

Max Act: 2.5349. Min Act: -0.0000

Data Index: 716711 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 3.6820. Min Range: -3.6820

Max Act: 2.6138. Min Act: -0.0000

Data Index: 70606 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 3.6820. Min Range: -3.6820

Max Act: 2.2981. Min Act: -0.0000

Data Index: 417847 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 3.6820. Min Range: -3.6820

Max Act: 2.1781. Min Act: -0.0000

Data Index: 363650 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 3.6820. Min Range: -3.6820

Max Act: 2.1633. Min Act: -0.0000

Data Index: 990727 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 3.6820. Min Range: -3.6820

Max Act: 2.1510. Min Act: -0.0000

Data Index: 201584 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 3.6820. Min Range: -3.6820

Max Act: 1.9618. Min Act: -0.0000

Data Index: 1120386 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 3.6820. Min Range: -3.6820

Max Act: 1.6513. Min Act: -0.0000

Data Index: 367118 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 3.6820. Min Range: -3.6820

Max Act: 1.8378. Min Act: 0.0000

Data Index: 1095686 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 3.6820. Min Range: -3.6820

Max Act: 1.6437. Min Act: 0.0000

Data Index: 105073 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 3.6820. Min Range: -3.6820

Max Act: 1.7480. Min Act: -0.0000

Data Index: 388750 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 3.6820. Min Range: -3.6820

Max Act: 1.5666. Min Act: -0.0000

Data Index: 657354 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 3.6820. Min Range: -3.6820

Max Act: 1.5902. Min Act: -0.0000

Data Index: 743421 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 3.6820. Min Range: -3.6820

Max Act: 1.6254. Min Act: -0.0000

Data Index: 651610 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 3.6820. Min Range: -3.6820

Max Act: 1.6072. Min Act: -0.0000

Data Index: 491926 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 3.6820. Min Range: -3.6820

Max Act: 1.5399. Min Act: -0.0000

Data Index: 1051915 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 3.6820. Min Range: -3.6820

Max Act: 1.4986. Min Act: -0.0000

Data Index: 695182 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 3.6820. Min Range: -3.6820

Max Act: 1.3350. Min Act: -0.0000

Data Index: 763701 (C4 (Web Text))

Max Activating Token Index: 1021