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

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

Neuron 3447 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: 0.0968. Min Range: -0.0968

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1086158 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0952. Min Act: -0.0000

Data Index: 463737 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0940. Min Act: -0.0000

Data Index: 754673 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1286706 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0887. Min Act: -0.0000

Data Index: 127053 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1257298 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0904. Min Act: -0.0001

Data Index: 59185 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0886. Min Act: -0.0000

Data Index: 95171 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0876. Min Act: -0.0001

Data Index: 530570 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0875. Min Act: -0.0000

Data Index: 82233 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0868. Min Act: -0.0000

Data Index: 59125 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1065830 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0855. Min Act: -0.0001

Data Index: 92985 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0821. Min Act: -0.0000

Data Index: 821512 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0847. Min Act: -0.0001

Data Index: 629330 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1403556 (Python Code)

Max Activating Token Index: 604

Text #16

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1287016 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0829. Min Act: -0.0000

Data Index: 491356 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0828. Min Act: -0.0001

Data Index: 1198213 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0800. Min Act: -0.0000

Data Index: 880892 (C4 (Web Text))

Max Activating Token Index: 294