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

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

Neuron 1812 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0319. Min Act: -0.0000

Data Index: 771541 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1006975 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1166016 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.5878. Min Act: -0.0000

Data Index: 798138 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1260801 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9179. Min Act: -0.0000

Data Index: 1287649 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.7274. Min Act: -0.0000

Data Index: 791266 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.8397. Min Act: -0.0000

Data Index: 792914 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.7742. Min Act: -0.0000

Data Index: 431590 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1259013 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.7902. Min Act: -0.0000

Data Index: 510793 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1352793 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1120901 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.8094. Min Act: -0.0000

Data Index: 165119 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1047697 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.7406. Min Act: -0.0000

Data Index: 778147 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.6934. Min Act: -0.0000

Data Index: 423697 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.7562. Min Act: -0.0000

Data Index: 23766 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.7228. Min Act: -0.0000

Data Index: 24682 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.7392. Min Act: -0.0000

Data Index: 761108 (C4 (Web Text))

Max Activating Token Index: 799