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

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

Neuron 4133 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: 0.6610. Min Range: -0.6610

Max Act: 0.6610. Min Act: -0.0000

Data Index: 39381 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5045. Min Act: -0.0000

Data Index: 282274 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4454. Min Act: -0.0000

Data Index: 634181 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1315524 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4031. Min Act: -0.0000

Data Index: 882537 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4109. Min Act: -0.0000

Data Index: 768688 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.3968. Min Act: -0.0000

Data Index: 789338 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4144. Min Act: -0.0000

Data Index: 466177 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4078. Min Act: -0.0000

Data Index: 821407 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.3992. Min Act: -0.0000

Data Index: 983568 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.3986. Min Act: -0.0000

Data Index: 595832 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.3840. Min Act: -0.0000

Data Index: 113756 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4043. Min Act: -0.0000

Data Index: 420609 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.3922. Min Act: -0.0000

Data Index: 902692 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.3660. Min Act: -0.0000

Data Index: 436725 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.3357. Min Act: -0.0000

Data Index: 870203 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.3730. Min Act: -0.0000

Data Index: 534252 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.3611. Min Act: -0.0000

Data Index: 586355 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.3676. Min Act: -0.0000

Data Index: 632252 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1228298 (C4 (Web Text))

Max Activating Token Index: 643