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

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

Neuron 160 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: 1.0847. Min Range: -1.0847

Max Act: 1.0847. Min Act: -0.0000

Data Index: 982870 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.8054. Min Act: -0.0000

Data Index: 975137 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.8383. Min Act: -0.0000

Data Index: 35996 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.8087. Min Act: -0.0000

Data Index: 477361 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.8318. Min Act: -0.0000

Data Index: 949603 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.8027. Min Act: -0.0000

Data Index: 419849 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1198777 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.7111. Min Act: -0.0000

Data Index: 953973 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.7323. Min Act: -0.0000

Data Index: 77492 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.7122. Min Act: -0.0000

Data Index: 467642 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.7469. Min Act: -0.0000

Data Index: 647475 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.7204. Min Act: -0.0000

Data Index: 440021 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1123631 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1016517 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.6870. Min Act: -0.0000

Data Index: 122663 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1257169 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.6645. Min Act: -0.0000

Data Index: 194682 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.6535. Min Act: -0.0000

Data Index: 696655 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.6420. Min Act: -0.0000

Data Index: 100256 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 1.0847. Min Range: -1.0847

Max Act: 0.6756. Min Act: -0.0000

Data Index: 337726 (C4 (Web Text))

Max Activating Token Index: 620