Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5605 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1013. Min Act: -0.0001

Data Index: 303612 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1314096 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0932. Min Act: -0.0001

Data Index: 972317 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1110913 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0910. Min Act: -0.0001

Data Index: 884271 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0836. Min Act: -0.0001

Data Index: 722463 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0898. Min Act: -0.0001

Data Index: 631396 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1199995 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0916. Min Act: -0.0001

Data Index: 567431 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0929. Min Act: -0.0001

Data Index: 481867 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0978. Min Act: -0.0001

Data Index: 400882 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0905. Min Act: -0.0001

Data Index: 151980 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0814. Min Act: -0.0001

Data Index: 854614 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1044214 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1137707 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0927. Min Act: -0.0001

Data Index: 528367 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0885. Min Act: -0.0001

Data Index: 593595 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1100112 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0806. Min Act: -0.0001

Data Index: 36121 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0806. Min Act: -0.0001

Data Index: 874160 (C4 (Web Text))

Max Activating Token Index: 166