Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1558 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0928. Min Act: -0.0001

Data Index: 697863 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0933. Min Act: -0.0001

Data Index: 1213495 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1177442 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0960. Min Act: -0.0001

Data Index: 979111 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1357916 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0860. Min Act: -0.0001

Data Index: 180556 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0904. Min Act: -0.0001

Data Index: 414579 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1359322 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0886. Min Act: -0.0001

Data Index: 876699 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0853. Min Act: -0.0001

Data Index: 576357 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0881. Min Act: -0.0001

Data Index: 573341 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0852. Min Act: -0.0001

Data Index: 801291 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0875. Min Act: -0.0001

Data Index: 969477 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0908. Min Act: -0.0001

Data Index: 978299 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0875. Min Act: -0.0001

Data Index: 901300 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1302806 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0831. Min Act: -0.0001

Data Index: 117834 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1320220 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0788. Min Act: -0.0001

Data Index: 21260 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0842. Min Act: -0.0001

Data Index: 77230 (C4 (Web Text))

Max Activating Token Index: 900