Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3717 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.9668. Min Act: -0.0000

Data Index: 310662 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.7079. Min Act: -0.0000

Data Index: 406099 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.3455. Min Act: -0.0000

Data Index: 1129539 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.0453. Min Act: -0.0001

Data Index: 1056035 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.0112. Min Act: -0.0000

Data Index: 855633 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.2202. Min Act: -0.0000

Data Index: 346532 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.1980. Min Act: -0.0001

Data Index: 317260 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.2508. Min Act: -0.0000

Data Index: 291299 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 2.9668. Min Range: -2.9668

Max Act: 1.9666. Min Act: -0.0000

Data Index: 1153497 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.1872. Min Act: -0.0000

Data Index: 690145 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.1661. Min Act: -0.0000

Data Index: 285753 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.0468. Min Act: -0.0000

Data Index: 253402 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.0358. Min Act: -0.0000

Data Index: 222919 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.1591. Min Act: -0.0000

Data Index: 313411 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 2.9668. Min Range: -2.9668

Max Act: 1.9940. Min Act: -0.0000

Data Index: 1345795 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.0141. Min Act: -0.0001

Data Index: 682008 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 2.9668. Min Range: -2.9668

Max Act: 1.7885. Min Act: -0.0000

Data Index: 631964 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 2.9668. Min Range: -2.9668

Max Act: 1.8846. Min Act: -0.0000

Data Index: 878093 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 2.9668. Min Range: -2.9668

Max Act: 1.8891. Min Act: -0.0000

Data Index: 614535 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 2.9668. Min Range: -2.9668

Max Act: 2.0878. Min Act: -0.0001

Data Index: 534608 (C4 (Web Text))

Max Activating Token Index: 36