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

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

Neuron 3805 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: 2.0157. Min Range: -2.0157

Max Act: 2.0157. Min Act: -0.0000

Data Index: 1151385 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.8078. Min Act: -0.0001

Data Index: 26557 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.8067. Min Act: -0.0000

Data Index: 1262587 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.7215. Min Act: -0.0001

Data Index: 961412 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.6964. Min Act: -0.0000

Data Index: 5817 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.6718. Min Act: -0.0000

Data Index: 1290976 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.6744. Min Act: -0.0001

Data Index: 1311214 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.7643. Min Act: -0.0001

Data Index: 596681 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.5543. Min Act: -0.0000

Data Index: 155466 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.6048. Min Act: -0.0000

Data Index: 1284715 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.6249. Min Act: -0.0000

Data Index: 670032 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.4873. Min Act: -0.0000

Data Index: 428697 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.5673. Min Act: -0.0001

Data Index: 892797 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.5583. Min Act: -0.0000

Data Index: 129818 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.5051. Min Act: -0.0000

Data Index: 1350016 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.5409. Min Act: -0.0000

Data Index: 753943 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.4987. Min Act: -0.0000

Data Index: 494078 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.5795. Min Act: -0.0001

Data Index: 463357 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.4857. Min Act: -0.0001

Data Index: 1340534 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.5192. Min Act: -0.0001

Data Index: 235856 (C4 (Web Text))

Max Activating Token Index: 568