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

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

Neuron 3286 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.7468. Min Act: -0.0001

Data Index: 240039 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6364. Min Act: -0.0001

Data Index: 307627 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6053. Min Act: -0.0001

Data Index: 819425 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5313. Min Act: -0.0001

Data Index: 434914 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.4538. Min Act: -0.0001

Data Index: 1052664 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5366. Min Act: -0.0001

Data Index: 603222 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5867. Min Act: -0.0001

Data Index: 760155 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5498. Min Act: -0.0001

Data Index: 125848 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5455. Min Act: -0.0001

Data Index: 469317 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.4943. Min Act: -0.0001

Data Index: 261665 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5501. Min Act: -0.0001

Data Index: 882683 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.4873. Min Act: -0.0001

Data Index: 534185 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5616. Min Act: -0.0001

Data Index: 1121999 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.4712. Min Act: -0.0001

Data Index: 514345 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5412. Min Act: -0.0001

Data Index: 747327 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5046. Min Act: -0.0001

Data Index: 1188448 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5338. Min Act: -0.0001

Data Index: 438259 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.4973. Min Act: -0.0001

Data Index: 421705 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.4543. Min Act: -0.0001

Data Index: 1095120 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5277. Min Act: -0.0001

Data Index: 571218 (C4 (Web Text))

Max Activating Token Index: 32