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

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

Neuron 3666 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.7973. Min Act: -0.0000

Data Index: 878769 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1834 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5664. Min Act: -0.0000

Data Index: 642382 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5830. Min Act: -0.0000

Data Index: 79716 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1240734 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5537. Min Act: -0.0000

Data Index: 900318 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1054152 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5243. Min Act: -0.0000

Data Index: 895069 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5738. Min Act: -0.0001

Data Index: 1143701 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.4761. Min Act: -0.0000

Data Index: 630809 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5325. Min Act: -0.0000

Data Index: 291653 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5263. Min Act: -0.0001

Data Index: 526157 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1198803 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1029363 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5134. Min Act: -0.0000

Data Index: 787388 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.4669. Min Act: -0.0000

Data Index: 499214 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.4552. Min Act: -0.0001

Data Index: 875837 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.4658. Min Act: -0.0000

Data Index: 473064 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.4777. Min Act: -0.0001

Data Index: 674182 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.4823. Min Act: -0.0000

Data Index: 353958 (C4 (Web Text))

Max Activating Token Index: 765