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

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

Neuron 3901 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: 1.4909. Min Range: -1.4909

Max Act: 1.4909. Min Act: -0.0001

Data Index: 972176 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.2163. Min Act: -0.0001

Data Index: 1095747 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.0266. Min Act: -0.0001

Data Index: 1248982 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.1093. Min Act: -0.0001

Data Index: 851520 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.0914. Min Act: -0.0001

Data Index: 939884 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.9928. Min Act: -0.0001

Data Index: 949726 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.9186. Min Act: -0.0001

Data Index: 1175830 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 1.4909. Min Range: -1.4909

Max Act: 1.0222. Min Act: -0.0001

Data Index: 597949 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.7552. Min Act: -0.0001

Data Index: 983899 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.7828. Min Act: -0.0001

Data Index: 861621 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.7709. Min Act: -0.0001

Data Index: 1058473 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.7482. Min Act: -0.0001

Data Index: 526602 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.9285. Min Act: -0.0001

Data Index: 18436 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.7437. Min Act: -0.0001

Data Index: 974804 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.7129. Min Act: -0.0001

Data Index: 1346006 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.6519. Min Act: -0.0001

Data Index: 187105 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.6924. Min Act: -0.0001

Data Index: 371850 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.6801. Min Act: -0.0001

Data Index: 197412 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.6348. Min Act: -0.0001

Data Index: 413495 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 1.4909. Min Range: -1.4909

Max Act: 0.6869. Min Act: -0.0001

Data Index: 807390 (C4 (Web Text))

Max Activating Token Index: 615