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

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

Neuron 2698 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: 1.1551. Min Range: -1.1551

Max Act: 1.1317. Min Act: -0.0001

Data Index: 575659 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.1551. Min Act: -0.0001

Data Index: 5483 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.1512. Min Act: -0.0001

Data Index: 1014559 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0532. Min Act: -0.0001

Data Index: 1344301 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0291. Min Act: -0.0001

Data Index: 526973 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0896. Min Act: -0.0001

Data Index: 43811 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9840. Min Act: -0.0001

Data Index: 152043 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0207. Min Act: -0.0001

Data Index: 1109961 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9754. Min Act: -0.0001

Data Index: 567248 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9904. Min Act: -0.0001

Data Index: 1010764 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9704. Min Act: -0.0001

Data Index: 891428 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9468. Min Act: -0.0001

Data Index: 1195996 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9784. Min Act: -0.0001

Data Index: 95910 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9513. Min Act: -0.0001

Data Index: 671883 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0091. Min Act: -0.0001

Data Index: 105263 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9391. Min Act: -0.0001

Data Index: 701715 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9328. Min Act: -0.0001

Data Index: 816139 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9837. Min Act: -0.0001

Data Index: 901093 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9135. Min Act: -0.0001

Data Index: 806936 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9332. Min Act: -0.0001

Data Index: 1267726 (C4 (Web Text))

Max Activating Token Index: 429