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

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

Neuron 143 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: 0.7957. Min Range: -0.7957

Max Act: 0.7699. Min Act: -0.0001

Data Index: 1286170 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.7957. Min Act: -0.0001

Data Index: 214673 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.7943. Min Act: -0.0001

Data Index: 1103864 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.7714. Min Act: -0.0001

Data Index: 219335 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.6882. Min Act: -0.0001

Data Index: 47523 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.6562. Min Act: -0.0001

Data Index: 595668 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.6283. Min Act: -0.0001

Data Index: 653477 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.6265. Min Act: -0.0001

Data Index: 927225 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.6175. Min Act: -0.0001

Data Index: 580365 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.6118. Min Act: -0.0001

Data Index: 1142321 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.5341. Min Act: -0.0001

Data Index: 833583 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.5353. Min Act: -0.0001

Data Index: 1297629 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.5889. Min Act: -0.0001

Data Index: 686562 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.4798. Min Act: -0.0001

Data Index: 405344 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.4959. Min Act: -0.0001

Data Index: 584447 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.5075. Min Act: -0.0001

Data Index: 455825 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.4859. Min Act: -0.0001

Data Index: 582468 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.4829. Min Act: -0.0001

Data Index: 508929 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.4865. Min Act: -0.0001

Data Index: 752349 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.7957. Min Range: -0.7957

Max Act: 0.4642. Min Act: -0.0001

Data Index: 1049212 (C4 (Web Text))

Max Activating Token Index: 30