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

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

Neuron 93 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5863. Min Act: -0.0001

Data Index: 169990 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5582. Min Act: -0.0001

Data Index: 1271638 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5263. Min Act: -0.0001

Data Index: 882136 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5796. Min Act: -0.0001

Data Index: 249809 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5351. Min Act: -0.0001

Data Index: 963254 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5271. Min Act: -0.0001

Data Index: 182391 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5176. Min Act: -0.0001

Data Index: 1216042 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5498. Min Act: -0.0001

Data Index: 1352934 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5277. Min Act: -0.0001

Data Index: 714127 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4955. Min Act: -0.0001

Data Index: 98978 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4900. Min Act: -0.0001

Data Index: 201056 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4870. Min Act: -0.0001

Data Index: 641224 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4992. Min Act: -0.0001

Data Index: 965601 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5014. Min Act: -0.0001

Data Index: 888631 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4815. Min Act: -0.0001

Data Index: 433844 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4981. Min Act: -0.0001

Data Index: 1215719 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4680. Min Act: -0.0001

Data Index: 286859 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4839. Min Act: -0.0001

Data Index: 416200 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4666. Min Act: -0.0001

Data Index: 868941 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4682. Min Act: -0.0001

Data Index: 1279384 (C4 (Web Text))

Max Activating Token Index: 636