Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2220 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.6994. Min Act: -0.0001

Data Index: 60850 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.7537. Min Act: -0.0001

Data Index: 171066 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5721. Min Act: -0.0001

Data Index: 700329 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5437. Min Act: -0.0001

Data Index: 55977 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5586. Min Act: -0.0001

Data Index: 283280 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5516. Min Act: -0.0001

Data Index: 454273 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5276. Min Act: -0.0001

Data Index: 1231947 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5656. Min Act: -0.0001

Data Index: 1189849 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5065. Min Act: -0.0001

Data Index: 967651 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.4973. Min Act: -0.0001

Data Index: 404043 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.4519. Min Act: -0.0001

Data Index: 71850 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5137. Min Act: -0.0001

Data Index: 882225 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5258. Min Act: -0.0001

Data Index: 662288 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.4917. Min Act: -0.0001

Data Index: 735340 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.4681. Min Act: -0.0001

Data Index: 192195 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.4786. Min Act: -0.0001

Data Index: 517430 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.4235. Min Act: -0.0001

Data Index: 789670 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.4318. Min Act: -0.0001

Data Index: 1046901 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.4706. Min Act: -0.0001

Data Index: 967327 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.4634. Min Act: -0.0001

Data Index: 193541 (C4 (Web Text))

Max Activating Token Index: 891