Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1992 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.9922. Min Act: -0.0000

Data Index: 72129 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.9474. Min Act: -0.0000

Data Index: 982725 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7842. Min Act: -0.0000

Data Index: 507653 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7828. Min Act: -0.0000

Data Index: 934678 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1103887 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7515. Min Act: 0.0000

Data Index: 883296 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7103. Min Act: 0.0001

Data Index: 565257 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1076883 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1140362 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7847. Min Act: -0.0000

Data Index: 164662 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7335. Min Act: -0.0000

Data Index: 160137 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.6978. Min Act: -0.0000

Data Index: 129036 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1140509 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1081907 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.6580. Min Act: 0.0000

Data Index: 862153 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.6868. Min Act: 0.0000

Data Index: 901953 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.6920. Min Act: 0.0000

Data Index: 919489 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1281961 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.6599. Min Act: 0.0001

Data Index: 446791 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.6926. Min Act: 0.0000

Data Index: 631364 (C4 (Web Text))

Max Activating Token Index: 259