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

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

Neuron 3830 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.6053. Min Act: -0.0001

Data Index: 1215066 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5479. Min Act: -0.0001

Data Index: 1199444 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4658. Min Act: -0.0001

Data Index: 858685 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5204. Min Act: -0.0001

Data Index: 833209 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4877. Min Act: -0.0001

Data Index: 630447 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4373. Min Act: -0.0001

Data Index: 216109 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4879. Min Act: -0.0001

Data Index: 862050 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.2481. Min Act: -0.0001

Data Index: 810555 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.3583. Min Act: -0.0001

Data Index: 1245907 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4102. Min Act: -0.0001

Data Index: 805777 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4198. Min Act: -0.0001

Data Index: 456663 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.3462. Min Act: -0.0001

Data Index: 195260 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4157. Min Act: -0.0001

Data Index: 469245 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4251. Min Act: -0.0001

Data Index: 1248718 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.3875. Min Act: -0.0001

Data Index: 706925 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.3802. Min Act: -0.0001

Data Index: 1118017 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4047. Min Act: -0.0001

Data Index: 267858 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.3885. Min Act: -0.0001

Data Index: 925210 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4135. Min Act: -0.0001

Data Index: 598817 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4154. Min Act: -0.0001

Data Index: 1029010 (C4 (Web Text))

Max Activating Token Index: 589