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

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

Neuron 3881 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.9010. Min Act: -0.0001

Data Index: 1068883 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8075. Min Act: -0.0001

Data Index: 273243 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7930. Min Act: -0.0001

Data Index: 1600537 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8332. Min Act: -0.0001

Data Index: 661387 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8165. Min Act: -0.0001

Data Index: 411063 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8023. Min Act: -0.0001

Data Index: 1265447 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7431. Min Act: -0.0001

Data Index: 41057 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7219. Min Act: -0.0001

Data Index: 533867 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8147. Min Act: -0.0001

Data Index: 1608700 (Python Code)

Max Activating Token Index: 743

Text #9

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7305. Min Act: -0.0001

Data Index: 223190 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7566. Min Act: -0.0001

Data Index: 1014305 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6871. Min Act: -0.0001

Data Index: 403010 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7311. Min Act: -0.0001

Data Index: 15576 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6885. Min Act: -0.0001

Data Index: 70444 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6349. Min Act: -0.0001

Data Index: 1208557 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7032. Min Act: -0.0001

Data Index: 209990 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6149. Min Act: -0.0001

Data Index: 1121017 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6495. Min Act: -0.0001

Data Index: 859730 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6680. Min Act: -0.0001

Data Index: 360145 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6653. Min Act: -0.0001

Data Index: 141809 (C4 (Web Text))

Max Activating Token Index: 343