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

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

Neuron 3593 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0849. Min Range: -3.0849

Max Act: 3.0849. Min Act: -0.0000

Data Index: 431332 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 3.0849. Min Range: -3.0849

Max Act: 2.9578. Min Act: -0.0000

Data Index: 1049006 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 3.0849. Min Range: -3.0849

Max Act: 2.4863. Min Act: 0.0000

Data Index: 108473 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 3.0849. Min Range: -3.0849

Max Act: 2.4999. Min Act: -0.0000

Data Index: 474566 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 3.0849. Min Range: -3.0849

Max Act: 2.5129. Min Act: -0.0000

Data Index: 1065360 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 3.0849. Min Range: -3.0849

Max Act: 2.3669. Min Act: -0.0000

Data Index: 1045399 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 3.0849. Min Range: -3.0849

Max Act: 2.2124. Min Act: -0.0000

Data Index: 887323 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 3.0849. Min Range: -3.0849

Max Act: 2.0839. Min Act: -0.0000

Data Index: 695230 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 3.0849. Min Range: -3.0849

Max Act: 2.0117. Min Act: -0.0000

Data Index: 935143 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 3.0849. Min Range: -3.0849

Max Act: 1.9823. Min Act: -0.0000

Data Index: 386296 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 3.0849. Min Range: -3.0849

Max Act: 1.8854. Min Act: -0.0000

Data Index: 474593 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 3.0849. Min Range: -3.0849

Max Act: 2.1066. Min Act: -0.0000

Data Index: 827878 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 3.0849. Min Range: -3.0849

Max Act: 1.7631. Min Act: -0.0000

Data Index: 64341 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 3.0849. Min Range: -3.0849

Max Act: 1.7501. Min Act: -0.0000

Data Index: 694903 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 3.0849. Min Range: -3.0849

Max Act: 1.8472. Min Act: -0.0000

Data Index: 177106 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 3.0849. Min Range: -3.0849

Max Act: 1.6038. Min Act: 0.0000

Data Index: 598477 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 3.0849. Min Range: -3.0849

Max Act: 1.8031. Min Act: -0.0000

Data Index: 1623168 (Python Code)

Max Activating Token Index: 397

Text #17

Max Range: 3.0849. Min Range: -3.0849

Max Act: 1.6866. Min Act: 0.0000

Data Index: 855272 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 3.0849. Min Range: -3.0849

Max Act: 1.6942. Min Act: -0.0000

Data Index: 140225 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 3.0849. Min Range: -3.0849

Max Act: 1.7755. Min Act: -0.0000

Data Index: 1192422 (C4 (Web Text))

Max Activating Token Index: 238