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

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

Neuron 885 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: 0.5473. Min Range: -0.5473

Max Act: 0.5473. Min Act: -0.0001

Data Index: 795285 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.4110. Min Act: -0.0001

Data Index: 1148106 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.4404. Min Act: -0.0001

Data Index: 193317 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.4126. Min Act: -0.0001

Data Index: 452612 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.3983. Min Act: -0.0001

Data Index: 60536 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.4179. Min Act: -0.0001

Data Index: 701187 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.3975. Min Act: -0.0001

Data Index: 871825 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.4124. Min Act: -0.0001

Data Index: 589382 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.4205. Min Act: -0.0001

Data Index: 725437 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.3782. Min Act: -0.0002

Data Index: 548752 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.3839. Min Act: -0.0001

Data Index: 1210123 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.3677. Min Act: -0.0001

Data Index: 1163499 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.4069. Min Act: -0.0002

Data Index: 77485 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.3543. Min Act: -0.0001

Data Index: 1157871 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.3721. Min Act: -0.0001

Data Index: 643913 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.3529. Min Act: -0.0001

Data Index: 13978 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.3278. Min Act: -0.0001

Data Index: 1249206 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.3783. Min Act: -0.0001

Data Index: 23751 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.3724. Min Act: -0.0002

Data Index: 960250 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.5473. Min Range: -0.5473

Max Act: 0.3499. Min Act: -0.0001

Data Index: 987910 (C4 (Web Text))

Max Activating Token Index: 176