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

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

Neuron 4600 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.8955. Min Act: -0.0001

Data Index: 1240787 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.8623. Min Act: -0.0001

Data Index: 1061501 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1082485 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7765. Min Act: -0.0001

Data Index: 645801 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7347. Min Act: -0.0001

Data Index: 1190667 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7347. Min Act: -0.0000

Data Index: 48222 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7547. Min Act: -0.0001

Data Index: 311213 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7159. Min Act: -0.0001

Data Index: 107321 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7050. Min Act: -0.0000

Data Index: 483629 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6889. Min Act: -0.0001

Data Index: 659354 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7116. Min Act: -0.0001

Data Index: 1059570 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7175. Min Act: -0.0001

Data Index: 1194330 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6705. Min Act: -0.0001

Data Index: 903377 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6879. Min Act: -0.0000

Data Index: 102094 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6667. Min Act: -0.0001

Data Index: 141815 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6868. Min Act: -0.0001

Data Index: 935120 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6840. Min Act: -0.0000

Data Index: 302160 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6787. Min Act: -0.0000

Data Index: 762043 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1039047 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6526. Min Act: -0.0000

Data Index: 670327 (C4 (Web Text))

Max Activating Token Index: 6