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

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

Neuron 298 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0887. Min Act: -0.0002

Data Index: 446355 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0781. Min Act: -0.0001

Data Index: 328993 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0714. Min Act: -0.0002

Data Index: 97610 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0731. Min Act: -0.0001

Data Index: 719651 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0686. Min Act: -0.0002

Data Index: 591816 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1236218 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0634. Min Act: -0.0001

Data Index: 897398 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0683. Min Act: -0.0001

Data Index: 654376 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0653. Min Act: -0.0002

Data Index: 474058 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0593. Min Act: -0.0001

Data Index: 10199 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1158398 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0609. Min Act: -0.0002

Data Index: 405125 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1248340 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0551. Min Act: -0.0001

Data Index: 384886 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1070850 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1023906 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1261312 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1216997 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0562. Min Act: -0.0001

Data Index: 801745 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0562. Min Act: -0.0001

Data Index: 752205 (C4 (Web Text))

Max Activating Token Index: 76