Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 842 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.1086. Min Act: -0.0000

Data Index: 557360 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.2250. Min Act: -0.0000

Data Index: 129279 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 2.2753. Min Range: -2.2753

Max Act: 2.2753. Min Act: -0.0000

Data Index: 419263 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.8540. Min Act: -0.0000

Data Index: 696088 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.9262. Min Act: -0.0000

Data Index: 470082 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.9125. Min Act: -0.0000

Data Index: 329736 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.8566. Min Act: -0.0000

Data Index: 357398 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.9164. Min Act: -0.0000

Data Index: 1206209 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.7984. Min Act: -0.0000

Data Index: 1253566 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.7836. Min Act: -0.0000

Data Index: 1161120 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.6680. Min Act: -0.0000

Data Index: 864999 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.7556. Min Act: -0.0000

Data Index: 678840 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.7347. Min Act: -0.0000

Data Index: 993118 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.8418. Min Act: -0.0000

Data Index: 316742 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.6385. Min Act: -0.0000

Data Index: 44040 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.8279. Min Act: -0.0000

Data Index: 994897 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.8092. Min Act: -0.0000

Data Index: 1002646 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.6149. Min Act: -0.0000

Data Index: 338094 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.6245. Min Act: -0.0000

Data Index: 105856 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 2.2753. Min Range: -2.2753

Max Act: 1.6139. Min Act: -0.0000

Data Index: 531828 (C4 (Web Text))

Max Activating Token Index: 955