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

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

Neuron 2199 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7729. Min Act: -0.0000

Data Index: 417681 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7633. Min Act: -0.0000

Data Index: 703304 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7637. Min Act: -0.0000

Data Index: 529539 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1353052 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7058. Min Act: -0.0001

Data Index: 1106535 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7189. Min Act: -0.0001

Data Index: 996941 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7345. Min Act: -0.0001

Data Index: 937776 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7142. Min Act: -0.0000

Data Index: 514007 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1102100 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1018101 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6605. Min Act: -0.0000

Data Index: 349118 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6828. Min Act: -0.0000

Data Index: 617612 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6575. Min Act: -0.0000

Data Index: 815738 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6745. Min Act: -0.0000

Data Index: 119303 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6149. Min Act: -0.0000

Data Index: 29312 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6716. Min Act: -0.0000

Data Index: 125042 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1268377 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6830. Min Act: -0.0000

Data Index: 848006 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6290. Min Act: -0.0000

Data Index: 74249 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1304681 (C4 (Web Text))

Max Activating Token Index: 217