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

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

Neuron 3899 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.2118. Min Act: -0.0001

Data Index: 950407 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1141970 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1217847 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1951. Min Act: -0.0000

Data Index: 712028 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1924. Min Act: -0.0001

Data Index: 429444 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1998. Min Act: -0.0000

Data Index: 695862 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1982. Min Act: -0.0001

Data Index: 35781 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1879. Min Act: -0.0000

Data Index: 800693 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1766. Min Act: -0.0000

Data Index: 157398 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1915. Min Act: -0.0000

Data Index: 441758 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1864. Min Act: -0.0001

Data Index: 340895 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1689. Min Act: -0.0001

Data Index: 1358877 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1773. Min Act: -0.0001

Data Index: 1044621 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1009906 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1653. Min Act: -0.0001

Data Index: 192950 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1237354 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1718. Min Act: -0.0001

Data Index: 57722 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1689. Min Act: -0.0000

Data Index: 714141 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1588. Min Act: -0.0000

Data Index: 117807 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1537. Min Act: -0.0000

Data Index: 419105 (C4 (Web Text))

Max Activating Token Index: 608