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

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

Neuron 5103 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1883. Min Range: -1.1883

Max Act: 1.1705. Min Act: -0.0001

Data Index: 829654 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 1.1883. Min Range: -1.1883

Max Act: 1.1883. Min Act: -0.0001

Data Index: 181360 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 1.1883. Min Range: -1.1883

Max Act: 1.1569. Min Act: -0.0001

Data Index: 917090 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 1.1883. Min Range: -1.1883

Max Act: 1.0059. Min Act: -0.0001

Data Index: 983488 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.9907. Min Act: -0.0001

Data Index: 390295 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 1.1883. Min Range: -1.1883

Max Act: 1.0234. Min Act: -0.0001

Data Index: 1112315 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 1.1883. Min Range: -1.1883

Max Act: 1.0120. Min Act: -0.0001

Data Index: 913254 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.9731. Min Act: -0.0001

Data Index: 1331037 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.9182. Min Act: -0.0001

Data Index: 1172158 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.9978. Min Act: -0.0001

Data Index: 297997 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.9843. Min Act: -0.0001

Data Index: 313685 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.9900. Min Act: -0.0001

Data Index: 1142665 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.9622. Min Act: -0.0001

Data Index: 969348 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.9189. Min Act: -0.0001

Data Index: 164922 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.9596. Min Act: -0.0001

Data Index: 116077 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.8853. Min Act: -0.0001

Data Index: 583916 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.9052. Min Act: -0.0001

Data Index: 758153 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.9359. Min Act: -0.0001

Data Index: 529764 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.9526. Min Act: -0.0001

Data Index: 357011 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 1.1883. Min Range: -1.1883

Max Act: 0.8877. Min Act: -0.0001

Data Index: 592454 (C4 (Web Text))

Max Activating Token Index: 175