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

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

Neuron 4992 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4400. Min Range: -3.4400

Max Act: 3.4400. Min Act: -0.0000

Data Index: 1347025 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 3.4400. Min Range: -3.4400

Max Act: 3.0461. Min Act: -0.0000

Data Index: 65906 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.7164. Min Act: -0.0000

Data Index: 41458 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.7046. Min Act: -0.0000

Data Index: 436994 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.5008. Min Act: -0.0000

Data Index: 261767 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.7897. Min Act: -0.0000

Data Index: 436098 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.5772. Min Act: 0.0000

Data Index: 505612 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.3917. Min Act: -0.0000

Data Index: 896887 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.5015. Min Act: 0.0002

Data Index: 768883 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.3768. Min Act: -0.0000

Data Index: 409194 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.4581. Min Act: 0.0000

Data Index: 249885 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.4417. Min Act: 0.0000

Data Index: 1207800 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.3920. Min Act: -0.0000

Data Index: 1255727 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.4111. Min Act: 0.0000

Data Index: 160535 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.3556. Min Act: 0.0000

Data Index: 484225 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.3561. Min Act: -0.0000

Data Index: 429525 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.3240. Min Act: -0.0000

Data Index: 273743 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.3101. Min Act: -0.0000

Data Index: 711495 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.2647. Min Act: -0.0000

Data Index: 1250821 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 3.4400. Min Range: -3.4400

Max Act: 2.2698. Min Act: -0.0000

Data Index: 543911 (C4 (Web Text))

Max Activating Token Index: 561