Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 856 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8974. Min Act: -0.0001

Data Index: 1072159 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8701. Min Act: -0.0001

Data Index: 453854 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8019. Min Act: -0.0001

Data Index: 114225 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7653. Min Act: -0.0001

Data Index: 530109 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7826. Min Act: -0.0001

Data Index: 99851 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7355. Min Act: -0.0001

Data Index: 581902 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.6731. Min Act: -0.0000

Data Index: 38867 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.6715. Min Act: -0.0001

Data Index: 1089351 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7112. Min Act: -0.0000

Data Index: 368166 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.6752. Min Act: -0.0001

Data Index: 326854 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.6529. Min Act: -0.0000

Data Index: 682466 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.6040. Min Act: -0.0001

Data Index: 433673 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.6379. Min Act: -0.0001

Data Index: 814869 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.6123. Min Act: -0.0001

Data Index: 1311118 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.5746. Min Act: -0.0000

Data Index: 383522 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.6086. Min Act: -0.0001

Data Index: 13925 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1216120 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.5673. Min Act: -0.0000

Data Index: 308496 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.5962. Min Act: -0.0001

Data Index: 1208300 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.5999. Min Act: -0.0000

Data Index: 260999 (C4 (Web Text))

Max Activating Token Index: 190