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

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

Neuron 910 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5919. Min Act: -0.0000

Data Index: 507543 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4699. Min Act: -0.0000

Data Index: 228345 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1258627 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4357. Min Act: -0.0000

Data Index: 941066 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4124. Min Act: -0.0000

Data Index: 919086 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1144206 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4383. Min Act: -0.0000

Data Index: 926308 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4077. Min Act: -0.0000

Data Index: 10159 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1003993 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.3960. Min Act: -0.0000

Data Index: 994531 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4023. Min Act: -0.0000

Data Index: 996513 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.3758. Min Act: -0.0000

Data Index: 811382 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.3950. Min Act: -0.0000

Data Index: 594021 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.3839. Min Act: -0.0000

Data Index: 319416 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.3692. Min Act: -0.0000

Data Index: 187589 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.3764. Min Act: -0.0000

Data Index: 330706 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.3662. Min Act: -0.0000

Data Index: 10161 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.3886. Min Act: -0.0000

Data Index: 798949 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.3764. Min Act: -0.0000

Data Index: 438913 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.3397. Min Act: -0.0000

Data Index: 755477 (C4 (Web Text))

Max Activating Token Index: 74