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

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

Neuron 536 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9804. Min Act: -0.0000

Data Index: 1189309 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1065322 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9280. Min Act: -0.0000

Data Index: 83171 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8608. Min Act: -0.0001

Data Index: 1232703 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9263. Min Act: -0.0001

Data Index: 556062 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9247. Min Act: -0.0000

Data Index: 382133 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9182. Min Act: -0.0001

Data Index: 121067 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8249. Min Act: -0.0001

Data Index: 668650 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9021. Min Act: -0.0001

Data Index: 352780 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8955. Min Act: -0.0000

Data Index: 914096 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8729. Min Act: -0.0001

Data Index: 692792 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8656. Min Act: -0.0001

Data Index: 181839 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8631. Min Act: -0.0000

Data Index: 528071 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9706. Min Act: -0.0000

Data Index: 168777 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8576. Min Act: -0.0000

Data Index: 224493 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8489. Min Act: -0.0001

Data Index: 817387 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8087. Min Act: -0.0001

Data Index: 1015098 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1294854 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8559. Min Act: -0.0001

Data Index: 725537 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8029. Min Act: -0.0000

Data Index: 774732 (C4 (Web Text))

Max Activating Token Index: 184