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

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

Neuron 4379 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.7178. Min Act: -0.0000

Data Index: 259208 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.7176. Min Act: -0.0000

Data Index: 382617 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.5917. Min Act: -0.0000

Data Index: 650049 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.4588. Min Act: -0.0000

Data Index: 291815 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.5263. Min Act: -0.0000

Data Index: 1245687 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.4046. Min Act: -0.0000

Data Index: 895142 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.4787. Min Act: -0.0000

Data Index: 743419 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.3935. Min Act: -0.0000

Data Index: 1060781 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.3625. Min Act: -0.0000

Data Index: 970479 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.3309. Min Act: -0.0000

Data Index: 255396 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.4468. Min Act: -0.0000

Data Index: 1044376 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.3860. Min Act: -0.0000

Data Index: 633560 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.3916. Min Act: -0.0000

Data Index: 844468 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.3059. Min Act: -0.0000

Data Index: 475885 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.3458. Min Act: -0.0000

Data Index: 523496 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.3676. Min Act: -0.0000

Data Index: 797131 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.3288. Min Act: -0.0000

Data Index: 204937 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.2541. Min Act: -0.0000

Data Index: 201487 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.3262. Min Act: -0.0000

Data Index: 828519 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.7178. Min Range: -1.7178

Max Act: 1.1704. Min Act: -0.0000

Data Index: 1555188 (Python Code)

Max Activating Token Index: 342