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

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

Neuron 1162 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: 1.9196. Min Range: -1.9196

Max Act: 1.9196. Min Act: -0.0001

Data Index: 594616 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 1.9196. Min Range: -1.9196

Max Act: 1.9149. Min Act: -0.0001

Data Index: 61504 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 1.9196. Min Range: -1.9196

Max Act: 1.7002. Min Act: -0.0001

Data Index: 1206908 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.9196. Min Range: -1.9196

Max Act: 1.5509. Min Act: -0.0001

Data Index: 1042453 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 1.9196. Min Range: -1.9196

Max Act: 1.5252. Min Act: -0.0001

Data Index: 1342641 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.7691. Min Act: -0.0001

Data Index: 1040852 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.7130. Min Act: -0.0001

Data Index: 390168 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.7549. Min Act: -0.0001

Data Index: 355350 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.7534. Min Act: -0.0001

Data Index: 11919 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.7392. Min Act: -0.0001

Data Index: 249290 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.6523. Min Act: -0.0001

Data Index: 856684 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.7093. Min Act: -0.0001

Data Index: 54127 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.7329. Min Act: -0.0001

Data Index: 360546 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.6709. Min Act: -0.0001

Data Index: 1107773 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.6651. Min Act: -0.0001

Data Index: 207527 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.7131. Min Act: -0.0001

Data Index: 285122 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.7362. Min Act: -0.0001

Data Index: 38759 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.7328. Min Act: -0.0001

Data Index: 380057 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.6592. Min Act: -0.0001

Data Index: 1036629 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 1.9196. Min Range: -1.9196

Max Act: 0.6941. Min Act: -0.0001

Data Index: 663443 (C4 (Web Text))

Max Activating Token Index: 310