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

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

Neuron 3777 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: 0.1033. Min Range: -0.1033

Max Act: 0.1001. Min Act: -0.0001

Data Index: 980372 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1198060 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0968. Min Act: -0.0001

Data Index: 178459 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0933. Min Act: -0.0001

Data Index: 680055 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1257327 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0938. Min Act: -0.0001

Data Index: 264613 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1051233 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0863. Min Act: -0.0001

Data Index: 388140 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0931. Min Act: -0.0001

Data Index: 38810 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0888. Min Act: -0.0001

Data Index: 502115 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0910. Min Act: -0.0001

Data Index: 441850 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0816. Min Act: -0.0001

Data Index: 244040 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1142689 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0815. Min Act: -0.0002

Data Index: 910118 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0801. Min Act: -0.0001

Data Index: 701585 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1137739 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0848. Min Act: -0.0002

Data Index: 551339 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0874. Min Act: -0.0001

Data Index: 419547 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0823. Min Act: -0.0002

Data Index: 353227 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1333849 (C4 (Web Text))

Max Activating Token Index: 93