Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3215 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7857. Min Range: -2.7857

Max Act: 2.7857. Min Act: -0.0000

Data Index: 1139695 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.9541. Min Act: -0.0000

Data Index: 190936 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.9118. Min Act: -0.0000

Data Index: 1130486 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.7513. Min Act: -0.0000

Data Index: 782226 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.8449. Min Act: -0.0000

Data Index: 657252 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.8468. Min Act: -0.0000

Data Index: 133287 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.8172. Min Act: -0.0000

Data Index: 653417 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.6791. Min Act: -0.0000

Data Index: 153148 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.6670. Min Act: -0.0000

Data Index: 160768 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.6179. Min Act: -0.0000

Data Index: 1138538 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.5978. Min Act: -0.0000

Data Index: 1347485 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.6972. Min Act: -0.0000

Data Index: 866109 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.5877. Min Act: -0.0000

Data Index: 160184 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.4905. Min Act: -0.0000

Data Index: 880367 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.5106. Min Act: -0.0000

Data Index: 197534 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.5018. Min Act: -0.0000

Data Index: 1215274 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.4332. Min Act: 0.0000

Data Index: 364192 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.4210. Min Act: -0.0000

Data Index: 1317715 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.4782. Min Act: -0.0000

Data Index: 646521 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 2.7857. Min Range: -2.7857

Max Act: 1.3725. Min Act: -0.0000

Data Index: 80008 (C4 (Web Text))

Max Activating Token Index: 757