Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1918 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.6127. Min Act: -0.0001

Data Index: 1026708 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5085. Min Act: -0.0001

Data Index: 312289 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5012. Min Act: -0.0001

Data Index: 736743 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5175. Min Act: -0.0001

Data Index: 791138 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5128. Min Act: -0.0001

Data Index: 335941 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4747. Min Act: -0.0001

Data Index: 370459 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4769. Min Act: -0.0001

Data Index: 1015954 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4405. Min Act: -0.0001

Data Index: 889037 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4475. Min Act: -0.0001

Data Index: 257633 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4857. Min Act: -0.0001

Data Index: 781185 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4848. Min Act: -0.0001

Data Index: 1109740 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4240. Min Act: -0.0001

Data Index: 1112153 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4673. Min Act: -0.0001

Data Index: 866574 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4072. Min Act: -0.0001

Data Index: 1178028 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4465. Min Act: -0.0001

Data Index: 270314 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4774. Min Act: -0.0001

Data Index: 220846 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4463. Min Act: -0.0001

Data Index: 395314 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4318. Min Act: -0.0001

Data Index: 1184980 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4610. Min Act: -0.0001

Data Index: 155704 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4556. Min Act: -0.0001

Data Index: 1029475 (C4 (Web Text))

Max Activating Token Index: 852