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

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

Neuron 3386 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.7460. Min Act: -0.0000

Data Index: 786953 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.7272. Min Act: -0.0000

Data Index: 693631 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.7468. Min Act: -0.0000

Data Index: 1120571 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1304144 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6767. Min Act: -0.0000

Data Index: 745662 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6163. Min Act: -0.0000

Data Index: 448914 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6136. Min Act: -0.0000

Data Index: 410764 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1011701 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5759. Min Act: -0.0000

Data Index: 374171 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5736. Min Act: -0.0000

Data Index: 846226 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5758. Min Act: -0.0000

Data Index: 754168 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6070. Min Act: -0.0000

Data Index: 490844 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5812. Min Act: -0.0000

Data Index: 216697 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1302071 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5732. Min Act: -0.0000

Data Index: 76214 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5545. Min Act: -0.0000

Data Index: 124620 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5735. Min Act: -0.0000

Data Index: 256797 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5893. Min Act: -0.0000

Data Index: 442519 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5840. Min Act: -0.0000

Data Index: 371978 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5645. Min Act: -0.0000

Data Index: 578900 (C4 (Web Text))

Max Activating Token Index: 928