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

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

Neuron 631 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: 1.1673. Min Range: -1.1673

Max Act: 1.1673. Min Act: -0.0001

Data Index: 293751 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 1.1673. Min Range: -1.1673

Max Act: 1.0680. Min Act: -0.0001

Data Index: 1034228 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 1.1673. Min Range: -1.1673

Max Act: 1.0764. Min Act: -0.0001

Data Index: 1341673 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9370. Min Act: -0.0001

Data Index: 941797 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9489. Min Act: -0.0001

Data Index: 74280 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9703. Min Act: -0.0001

Data Index: 590621 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9675. Min Act: -0.0001

Data Index: 1189781 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9569. Min Act: -0.0001

Data Index: 830292 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9575. Min Act: -0.0001

Data Index: 148812 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.8741. Min Act: -0.0001

Data Index: 1277358 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9728. Min Act: -0.0001

Data Index: 1229963 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9163. Min Act: -0.0001

Data Index: 199069 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9074. Min Act: -0.0001

Data Index: 1007016 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9045. Min Act: -0.0001

Data Index: 46134 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9577. Min Act: -0.0001

Data Index: 1260471 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9033. Min Act: -0.0001

Data Index: 860981 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.8442. Min Act: -0.0001

Data Index: 1319644 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.8917. Min Act: -0.0001

Data Index: 527629 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.8869. Min Act: -0.0001

Data Index: 1228232 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9027. Min Act: -0.0001

Data Index: 575155 (C4 (Web Text))

Max Activating Token Index: 74