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

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

Neuron 2976 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2031. Min Range: -1.2031

Max Act: 1.2031. Min Act: -0.0001

Data Index: 1152966 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 1.2031. Min Range: -1.2031

Max Act: 1.0368. Min Act: -0.0002

Data Index: 251504 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9985. Min Act: -0.0002

Data Index: 722573 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8787. Min Act: -0.0002

Data Index: 453947 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9171. Min Act: -0.0002

Data Index: 848657 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8754. Min Act: -0.0001

Data Index: 639169 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9005. Min Act: -0.0001

Data Index: 788654 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9016. Min Act: -0.0002

Data Index: 524653 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9216. Min Act: -0.0001

Data Index: 111491 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8469. Min Act: -0.0001

Data Index: 912010 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8228. Min Act: -0.0001

Data Index: 1036929 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.7945. Min Act: -0.0002

Data Index: 875244 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8773. Min Act: -0.0002

Data Index: 87853 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8631. Min Act: -0.0002

Data Index: 143347 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8603. Min Act: -0.0001

Data Index: 1183900 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8532. Min Act: -0.0001

Data Index: 989831 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.7999. Min Act: -0.0001

Data Index: 630442 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8765. Min Act: -0.0001

Data Index: 1043117 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8135. Min Act: -0.0001

Data Index: 234064 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.7279. Min Act: -0.0001

Data Index: 600346 (C4 (Web Text))

Max Activating Token Index: 685