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

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

Neuron 3672 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.6768. Min Act: -0.0000

Data Index: 379059 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.6516. Min Act: -0.0000

Data Index: 55338 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.4638. Min Act: -0.0000

Data Index: 1283715 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.5702. Min Act: -0.0000

Data Index: 420068 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.6797. Min Act: -0.0000

Data Index: 307378 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.5008. Min Act: -0.0000

Data Index: 446313 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.4668. Min Act: -0.0000

Data Index: 172738 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.4653. Min Act: -0.0000

Data Index: 909758 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.5004. Min Act: -0.0000

Data Index: 454215 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.3468. Min Act: -0.0000

Data Index: 16391 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.7557. Min Act: -0.0000

Data Index: 294721 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.4722. Min Act: -0.0000

Data Index: 194030 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.3218. Min Act: -0.0000

Data Index: 1353036 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.4390. Min Act: -0.0000

Data Index: 458329 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.3846. Min Act: -0.0000

Data Index: 787194 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.4910. Min Act: -0.0000

Data Index: 206754 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.2108. Min Act: -0.0000

Data Index: 92895 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.2955. Min Act: -0.0000

Data Index: 1051191 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.3805. Min Act: -0.0000

Data Index: 813552 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 2.7557. Min Range: -2.7557

Max Act: 2.5134. Min Act: -0.0000

Data Index: 604686 (C4 (Web Text))

Max Activating Token Index: 976