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

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

Neuron 3209 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0399. Min Range: -1.0399

Max Act: 1.0399. Min Act: -0.0001

Data Index: 18041 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9850. Min Act: -0.0000

Data Index: 764605 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9870. Min Act: -0.0000

Data Index: 201803 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9626. Min Act: -0.0000

Data Index: 518430 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1121305 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1070341 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1022620 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1328470 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8097. Min Act: -0.0000

Data Index: 344481 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8549. Min Act: -0.0000

Data Index: 846742 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.6934. Min Act: -0.0000

Data Index: 80319 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7951. Min Act: -0.0000

Data Index: 380917 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7789. Min Act: -0.0000

Data Index: 1076829 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1078048 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7314. Min Act: -0.0000

Data Index: 667686 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7636. Min Act: -0.0000

Data Index: 622349 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8073. Min Act: -0.0000

Data Index: 946498 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8008. Min Act: -0.0000

Data Index: 815956 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1188045 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7210. Min Act: -0.0000

Data Index: 658505 (C4 (Web Text))

Max Activating Token Index: 367