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

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

Neuron 3612 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: 5.6031. Min Range: -5.6031

Max Act: 5.6031. Min Act: -0.0001

Data Index: 63757 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 5.6031. Min Range: -5.6031

Max Act: 5.3936. Min Act: -0.0001

Data Index: 234398 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 5.6031. Min Range: -5.6031

Max Act: 5.2214. Min Act: -0.0001

Data Index: 742284 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 5.6031. Min Range: -5.6031

Max Act: 5.0145. Min Act: -0.0001

Data Index: 1313524 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.9077. Min Act: -0.0001

Data Index: 215883 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.7793. Min Act: -0.0001

Data Index: 969366 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.5275. Min Act: -0.0001

Data Index: 49426 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.4953. Min Act: -0.0001

Data Index: 1160884 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.3082. Min Act: -0.0001

Data Index: 486533 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.3114. Min Act: -0.0001

Data Index: 492053 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.0698. Min Act: -0.0001

Data Index: 7759 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.1749. Min Act: -0.0001

Data Index: 350964 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.1646. Min Act: -0.0001

Data Index: 661584 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.3195. Min Act: -0.0001

Data Index: 461941 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.3137. Min Act: -0.0001

Data Index: 476382 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.2917. Min Act: -0.0001

Data Index: 755760 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 5.6031. Min Range: -5.6031

Max Act: 3.9695. Min Act: -0.0001

Data Index: 1160836 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.0898. Min Act: -0.0001

Data Index: 168157 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 5.6031. Min Range: -5.6031

Max Act: 4.0367. Min Act: -0.0001

Data Index: 527452 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 5.6031. Min Range: -5.6031

Max Act: 3.9978. Min Act: -0.0001

Data Index: 668038 (C4 (Web Text))

Max Activating Token Index: 905