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

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

Neuron 3379 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.5017. Min Act: -0.0001

Data Index: 792780 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.5162. Min Act: -0.0001

Data Index: 273679 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.5083. Min Act: -0.0001

Data Index: 849645 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4840. Min Act: -0.0001

Data Index: 1186206 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4505. Min Act: -0.0001

Data Index: 629063 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4588. Min Act: -0.0001

Data Index: 388099 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4698. Min Act: -0.0001

Data Index: 149191 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4516. Min Act: -0.0001

Data Index: 158685 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4380. Min Act: -0.0001

Data Index: 439900 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3953. Min Act: -0.0001

Data Index: 353883 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1206547 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4560. Min Act: -0.0001

Data Index: 1297221 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4527. Min Act: -0.0001

Data Index: 1010047 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4222. Min Act: -0.0001

Data Index: 621467 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4210. Min Act: -0.0001

Data Index: 358127 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3937. Min Act: -0.0001

Data Index: 110996 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4195. Min Act: -0.0001

Data Index: 686001 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4061. Min Act: -0.0001

Data Index: 1310818 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4354. Min Act: -0.0001

Data Index: 253609 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4198. Min Act: -0.0001

Data Index: 114060 (C4 (Web Text))

Max Activating Token Index: 132