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

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

Neuron 1250 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: 1.7113. Min Range: -1.7113

Max Act: 1.7113. Min Act: -0.0001

Data Index: 1123757 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.4301. Min Act: -0.0001

Data Index: 483174 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.4408. Min Act: -0.0001

Data Index: 812948 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.3077. Min Act: -0.0001

Data Index: 822404 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.3056. Min Act: -0.0001

Data Index: 1135700 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.2962. Min Act: -0.0001

Data Index: 1019956 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.1683. Min Act: -0.0001

Data Index: 671547 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.2347. Min Act: -0.0001

Data Index: 500090 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.2141. Min Act: -0.0001

Data Index: 276308 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.2004. Min Act: -0.0001

Data Index: 952893 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.1507. Min Act: -0.0001

Data Index: 118425 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.1900. Min Act: -0.0001

Data Index: 1114332 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.0663. Min Act: -0.0001

Data Index: 839376 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.2514. Min Act: -0.0001

Data Index: 399840 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.0000. Min Act: -0.0001

Data Index: 654686 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.2075. Min Act: -0.0001

Data Index: 1161545 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.0974. Min Act: -0.0001

Data Index: 66150 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.1470. Min Act: -0.0001

Data Index: 1296491 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 1.7113. Min Range: -1.7113

Max Act: 0.9166. Min Act: -0.0001

Data Index: 435908 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 1.7113. Min Range: -1.7113

Max Act: 1.1295. Min Act: -0.0001

Data Index: 867647 (C4 (Web Text))

Max Activating Token Index: 52