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

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

Neuron 2416 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1207. Min Act: -0.0000

Data Index: 828513 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1087. Min Act: -0.0000

Data Index: 757702 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1102. Min Act: -0.0000

Data Index: 558698 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1056. Min Act: -0.0000

Data Index: 986905 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1352910 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0951. Min Act: -0.0000

Data Index: 355563 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0912. Min Act: -0.0000

Data Index: 212261 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0919. Min Act: -0.0000

Data Index: 96152 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0924. Min Act: -0.0000

Data Index: 295182 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1271601 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0902. Min Act: -0.0000

Data Index: 190847 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0932. Min Act: -0.0000

Data Index: 981025 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0917. Min Act: -0.0000

Data Index: 710446 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0862. Min Act: -0.0000

Data Index: 67006 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0899. Min Act: -0.0000

Data Index: 975289 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1299236 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1225352 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0882. Min Act: -0.0000

Data Index: 933433 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0839. Min Act: -0.0000

Data Index: 590300 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1283527 (C4 (Web Text))

Max Activating Token Index: 105