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

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

Neuron 1620 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: 1.2392. Min Range: -1.2392

Max Act: 1.2392. Min Act: -0.0000

Data Index: 359104 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.9955. Min Act: -0.0000

Data Index: 652761 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 1.2392. Min Range: -1.2392

Max Act: 1.0186. Min Act: -0.0000

Data Index: 325185 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1096000 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1175679 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.9236. Min Act: -0.0000

Data Index: 636121 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.9422. Min Act: -0.0000

Data Index: 921163 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1036947 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.9411. Min Act: -0.0000

Data Index: 923182 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.9109. Min Act: -0.0000

Data Index: 797984 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.9319. Min Act: -0.0000

Data Index: 570096 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.9136. Min Act: -0.0000

Data Index: 841990 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1004786 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.9096. Min Act: -0.0000

Data Index: 774754 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1081811 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.8883. Min Act: -0.0000

Data Index: 946831 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.8897. Min Act: -0.0000

Data Index: 999501 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.8746. Min Act: -0.0000

Data Index: 235184 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.8825. Min Act: -0.0000

Data Index: 440802 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 1.2392. Min Range: -1.2392

Max Act: 0.8390. Min Act: -0.0000

Data Index: 933390 (C4 (Web Text))

Max Activating Token Index: 634