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

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

Neuron 412 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: 13.8079. Min Range: -13.8079

Max Act: 13.8079. Min Act: -0.0001

Data Index: 1194722 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 13.8079. Min Range: -13.8079

Max Act: 13.5217. Min Act: -0.0000

Data Index: 867411 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 13.8079. Min Range: -13.8079

Max Act: 13.1237. Min Act: -0.0000

Data Index: 680790 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 13.8079. Min Range: -13.8079

Max Act: 12.5086. Min Act: -0.0001

Data Index: 1117160 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 13.8079. Min Range: -13.8079

Max Act: 12.5484. Min Act: -0.0001

Data Index: 474547 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 13.8079. Min Range: -13.8079

Max Act: 12.7870. Min Act: -0.0001

Data Index: 792613 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 13.8079. Min Range: -13.8079

Max Act: 12.4542. Min Act: -0.0000

Data Index: 279236 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 13.8079. Min Range: -13.8079

Max Act: 12.1791. Min Act: -0.0000

Data Index: 948539 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 13.8079. Min Range: -13.8079

Max Act: 11.6321. Min Act: -0.0000

Data Index: 65163 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 13.8079. Min Range: -13.8079

Max Act: 11.6056. Min Act: -0.0001

Data Index: 746063 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 13.8079. Min Range: -13.8079

Max Act: 12.0855. Min Act: -0.0000

Data Index: 1128298 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 13.8079. Min Range: -13.8079

Max Act: 11.7141. Min Act: -0.0000

Data Index: 1354826 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 13.8079. Min Range: -13.8079

Max Act: 3.2415. Min Act: -0.0000

Data Index: 891594 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 13.8079. Min Range: -13.8079

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1191594 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 13.8079. Min Range: -13.8079

Max Act: 10.7793. Min Act: -0.0000

Data Index: 774296 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 13.8079. Min Range: -13.8079

Max Act: 10.9732. Min Act: -0.0001

Data Index: 1582124 (Python Code)

Max Activating Token Index: 201

Text #16

Max Range: 13.8079. Min Range: -13.8079

Max Act: 7.0035. Min Act: -0.0000

Data Index: 1632232 (Python Code)

Max Activating Token Index: 410

Text #17

Max Range: 13.8079. Min Range: -13.8079

Max Act: 6.5695. Min Act: -0.0001

Data Index: 417831 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 13.8079. Min Range: -13.8079

Max Act: 7.4516. Min Act: -0.0001

Data Index: 809911 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 13.8079. Min Range: -13.8079

Max Act: 3.1459. Min Act: -0.0000

Data Index: 656307 (C4 (Web Text))

Max Activating Token Index: 68