Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3333 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.8777. Min Act: -0.0001

Data Index: 1318249 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6853. Min Act: -0.0001

Data Index: 889338 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6242. Min Act: -0.0001

Data Index: 782359 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6750. Min Act: -0.0001

Data Index: 289685 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6697. Min Act: -0.0001

Data Index: 35394 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6712. Min Act: -0.0001

Data Index: 599954 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6566. Min Act: -0.0001

Data Index: 52095 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6309. Min Act: -0.0001

Data Index: 1104749 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6416. Min Act: -0.0001

Data Index: 886963 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.5617. Min Act: -0.0001

Data Index: 871605 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6011. Min Act: -0.0001

Data Index: 725537 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.5724. Min Act: -0.0001

Data Index: 1192233 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6141. Min Act: -0.0001

Data Index: 449831 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.5463. Min Act: -0.0001

Data Index: 488796 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.5148. Min Act: -0.0001

Data Index: 340700 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.5683. Min Act: -0.0001

Data Index: 727702 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.5620. Min Act: -0.0001

Data Index: 1148505 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6042. Min Act: -0.0001

Data Index: 185243 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.5186. Min Act: -0.0001

Data Index: 277917 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.5163. Min Act: -0.0001

Data Index: 142932 (C4 (Web Text))

Max Activating Token Index: 266