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

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

Neuron 4125 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1073589 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1341383 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.8143. Min Act: -0.0000

Data Index: 329145 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7887. Min Act: -0.0000

Data Index: 306573 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6986. Min Act: -0.0000

Data Index: 829443 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7678. Min Act: -0.0000

Data Index: 965764 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7311. Min Act: -0.0000

Data Index: 866683 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6781. Min Act: -0.0000

Data Index: 193815 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7173. Min Act: -0.0000

Data Index: 423653 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7781. Min Act: -0.0000

Data Index: 1167832 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6983. Min Act: -0.0000

Data Index: 612590 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1055268 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7092. Min Act: -0.0000

Data Index: 914400 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1188062 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6455. Min Act: -0.0000

Data Index: 217656 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6821. Min Act: -0.0000

Data Index: 20700 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6841. Min Act: -0.0000

Data Index: 332078 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1348591 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6835. Min Act: -0.0000

Data Index: 6026 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6625. Min Act: -0.0000

Data Index: 273534 (C4 (Web Text))

Max Activating Token Index: 93