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

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

Neuron 1775 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0746. Min Range: -2.0746

Max Act: 2.0746. Min Act: -0.0000

Data Index: 998603 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.8645. Min Act: -0.0000

Data Index: 1157531 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.8714. Min Act: -0.0000

Data Index: 648039 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.8288. Min Act: -0.0000

Data Index: 320674 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.9238. Min Act: -0.0000

Data Index: 559659 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 2.0746. Min Range: -2.0746

Max Act: 2.0140. Min Act: -0.0000

Data Index: 263460 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.8774. Min Act: -0.0000

Data Index: 90254 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.9216. Min Act: -0.0000

Data Index: 368554 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.9065. Min Act: -0.0000

Data Index: 196754 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.7003. Min Act: -0.0000

Data Index: 192583 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.6917. Min Act: -0.0000

Data Index: 851170 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.5899. Min Act: -0.0000

Data Index: 1214016 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.6752. Min Act: -0.0000

Data Index: 269603 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.7194. Min Act: -0.0000

Data Index: 608974 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.7272. Min Act: -0.0000

Data Index: 76693 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.6202. Min Act: -0.0000

Data Index: 473204 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.7072. Min Act: -0.0000

Data Index: 1140087 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.6939. Min Act: -0.0000

Data Index: 1185823 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.6553. Min Act: -0.0000

Data Index: 661881 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 2.0746. Min Range: -2.0746

Max Act: 1.6135. Min Act: -0.0000

Data Index: 1244616 (C4 (Web Text))

Max Activating Token Index: 977