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

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

Neuron 3913 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0013. Min Range: -1.0013

Max Act: 1.0013. Min Act: -0.0001

Data Index: 90034 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.9318. Min Act: -0.0001

Data Index: 714290 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.9563. Min Act: -0.0001

Data Index: 215382 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.8400. Min Act: -0.0001

Data Index: 1162161 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.7919. Min Act: -0.0001

Data Index: 1332549 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.8066. Min Act: -0.0001

Data Index: 206756 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.8140. Min Act: -0.0001

Data Index: 1163171 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.7820. Min Act: -0.0001

Data Index: 893319 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.8868. Min Act: -0.0001

Data Index: 54294 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.8245. Min Act: -0.0001

Data Index: 1219169 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.8041. Min Act: -0.0001

Data Index: 640443 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.7895. Min Act: -0.0001

Data Index: 876015 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.7616. Min Act: -0.0001

Data Index: 450573 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.7380. Min Act: -0.0001

Data Index: 407499 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.7540. Min Act: -0.0001

Data Index: 64152 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.7070. Min Act: -0.0001

Data Index: 388463 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.8212. Min Act: -0.0001

Data Index: 905671 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.6549. Min Act: -0.0001

Data Index: 1327614 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.6996. Min Act: -0.0001

Data Index: 725714 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 1.0013. Min Range: -1.0013

Max Act: 0.7468. Min Act: -0.0001

Data Index: 837643 (C4 (Web Text))

Max Activating Token Index: 943