Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3616 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.0167. Min Act: -0.0000

Data Index: 695652 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.1459. Min Act: -0.0000

Data Index: 736511 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.0293. Min Act: -0.0000

Data Index: 599849 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.1031. Min Act: -0.0000

Data Index: 602064 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 1.1459. Min Range: -1.1459

Max Act: 1.0256. Min Act: 0.0000

Data Index: 1294850 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.9701. Min Act: -0.0000

Data Index: 187706 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.9018. Min Act: -0.0000

Data Index: 303839 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1119355 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1420294 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.8480. Min Act: 0.0000

Data Index: 469442 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.8535. Min Act: -0.0000

Data Index: 535710 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.8117. Min Act: -0.0000

Data Index: 34567 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.7860. Min Act: -0.0000

Data Index: 811746 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.8041. Min Act: 0.0000

Data Index: 157069 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.7524. Min Act: -0.0000

Data Index: 861996 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.7100. Min Act: -0.0000

Data Index: 625052 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.7342. Min Act: -0.0000

Data Index: 27667 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1208912 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.7289. Min Act: 0.0000

Data Index: 408574 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.1459. Min Range: -1.1459

Max Act: 0.7025. Min Act: -0.0000

Data Index: 733899 (C4 (Web Text))

Max Activating Token Index: 418