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

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

Neuron 2636 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: 1.9469. Min Range: -1.9469

Max Act: 1.9469. Min Act: -0.0000

Data Index: 143771 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.3543. Min Act: -0.0000

Data Index: 989041 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.6739. Min Act: -0.0001

Data Index: 284424 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.7076. Min Act: -0.0000

Data Index: 1099828 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.4162. Min Act: -0.0000

Data Index: 570015 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.6713. Min Act: -0.0000

Data Index: 223082 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.7205. Min Act: -0.0001

Data Index: 1150876 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.7622. Min Act: -0.0001

Data Index: 616152 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.8518. Min Act: -0.0000

Data Index: 1014273 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.7112. Min Act: -0.0001

Data Index: 349254 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.7144. Min Act: -0.0000

Data Index: 460767 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.4872. Min Act: -0.0001

Data Index: 380411 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.5724. Min Act: -0.0000

Data Index: 1192143 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.6827. Min Act: -0.0000

Data Index: 802262 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.3317. Min Act: -0.0001

Data Index: 725399 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.8435. Min Act: -0.0000

Data Index: 1184019 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.6182. Min Act: -0.0000

Data Index: 856587 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.7490. Min Act: -0.0000

Data Index: 321074 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.7962. Min Act: -0.0000

Data Index: 1353952 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 1.9469. Min Range: -1.9469

Max Act: 1.5261. Min Act: -0.0000

Data Index: 1346499 (C4 (Web Text))

Max Activating Token Index: 431