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

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

Neuron 3014 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.5127. Min Act: -0.0001

Data Index: 723913 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4814. Min Act: -0.0000

Data Index: 629717 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1354841 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4120. Min Act: -0.0001

Data Index: 804613 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4053. Min Act: -0.0000

Data Index: 207503 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3956. Min Act: -0.0000

Data Index: 350430 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4261. Min Act: -0.0000

Data Index: 55386 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1276550 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3533. Min Act: -0.0001

Data Index: 1054020 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3437. Min Act: -0.0000

Data Index: 101162 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3622. Min Act: -0.0001

Data Index: 1354847 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3732. Min Act: -0.0001

Data Index: 1127603 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3448. Min Act: -0.0000

Data Index: 530266 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3534. Min Act: -0.0001

Data Index: 651501 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3247. Min Act: -0.0000

Data Index: 781548 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3574. Min Act: -0.0000

Data Index: 788327 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3237. Min Act: -0.0000

Data Index: 352776 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3490. Min Act: -0.0000

Data Index: 354787 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3384. Min Act: -0.0001

Data Index: 287080 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3244. Min Act: -0.0001

Data Index: 1039814 (C4 (Web Text))

Max Activating Token Index: 956