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

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

Neuron 3750 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3989. Min Range: -4.3989

Max Act: 4.3989. Min Act: -0.0000

Data Index: 390342 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 4.3989. Min Range: -4.3989

Max Act: 3.2848. Min Act: -0.0001

Data Index: 1356727 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 4.3989. Min Range: -4.3989

Max Act: 3.0222. Min Act: -0.0001

Data Index: 530189 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 4.3989. Min Range: -4.3989

Max Act: 3.2073. Min Act: -0.0000

Data Index: 672771 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 4.3989. Min Range: -4.3989

Max Act: 3.0203. Min Act: -0.0001

Data Index: 653188 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 4.3989. Min Range: -4.3989

Max Act: 2.8941. Min Act: -0.0000

Data Index: 365567 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 4.3989. Min Range: -4.3989

Max Act: 3.5887. Min Act: -0.0001

Data Index: 723611 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 4.3989. Min Range: -4.3989

Max Act: 2.8193. Min Act: -0.0001

Data Index: 534163 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 4.3989. Min Range: -4.3989

Max Act: 3.1965. Min Act: -0.0001

Data Index: 974590 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 4.3989. Min Range: -4.3989

Max Act: 3.0024. Min Act: -0.0000

Data Index: 969135 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 4.3989. Min Range: -4.3989

Max Act: 2.5784. Min Act: -0.0001

Data Index: 1089551 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 4.3989. Min Range: -4.3989

Max Act: 2.8400. Min Act: -0.0001

Data Index: 159167 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 4.3989. Min Range: -4.3989

Max Act: 2.8617. Min Act: -0.0001

Data Index: 773703 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 4.3989. Min Range: -4.3989

Max Act: 2.9754. Min Act: -0.0001

Data Index: 1136872 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 4.3989. Min Range: -4.3989

Max Act: 2.8143. Min Act: -0.0001

Data Index: 488612 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 4.3989. Min Range: -4.3989

Max Act: 2.6924. Min Act: -0.0000

Data Index: 1146336 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 4.3989. Min Range: -4.3989

Max Act: 2.5543. Min Act: -0.0000

Data Index: 935922 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 4.3989. Min Range: -4.3989

Max Act: 2.5476. Min Act: -0.0000

Data Index: 1105125 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 4.3989. Min Range: -4.3989

Max Act: 2.6436. Min Act: -0.0001

Data Index: 506989 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 4.3989. Min Range: -4.3989

Max Act: 2.5822. Min Act: -0.0000

Data Index: 32695 (C4 (Web Text))

Max Activating Token Index: 253