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

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

Neuron 1632 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.6562. Min Act: -0.0000

Data Index: 901247 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.5717. Min Act: -0.0000

Data Index: 874602 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.5791. Min Act: -0.0000

Data Index: 146888 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3843. Min Act: -0.0000

Data Index: 1201562 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3584. Min Act: -0.0001

Data Index: 942134 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3481. Min Act: -0.0000

Data Index: 833518 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.6170. Min Act: -0.0000

Data Index: 1141732 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3145. Min Act: -0.0000

Data Index: 245174 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.2304. Min Act: -0.0000

Data Index: 868759 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3620. Min Act: -0.0000

Data Index: 219625 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.1999. Min Act: -0.0000

Data Index: 1182333 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3046. Min Act: -0.0000

Data Index: 581191 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.0791. Min Act: -0.0000

Data Index: 426444 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.0557. Min Act: -0.0000

Data Index: 523060 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 3.6562. Min Range: -3.6562

Max Act: 2.7420. Min Act: -0.0000

Data Index: 425738 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 3.6562. Min Range: -3.6562

Max Act: 2.9067. Min Act: -0.0000

Data Index: 1125479 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 3.6562. Min Range: -3.6562

Max Act: 2.6209. Min Act: -0.0000

Data Index: 1257835 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.0218. Min Act: -0.0000

Data Index: 1086466 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 3.6562. Min Range: -3.6562

Max Act: 2.5675. Min Act: -0.0000

Data Index: 1019791 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 3.6562. Min Range: -3.6562

Max Act: 2.6342. Min Act: -0.0000

Data Index: 186030 (C4 (Web Text))

Max Activating Token Index: 845