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

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

Neuron 20 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.6224. Min Range: -5.6224

Max Act: 5.6224. Min Act: -0.0000

Data Index: 465138 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 5.6224. Min Range: -5.6224

Max Act: 3.8505. Min Act: -0.0000

Data Index: 1104896 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 5.6224. Min Range: -5.6224

Max Act: 3.7559. Min Act: -0.0000

Data Index: 132335 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 5.6224. Min Range: -5.6224

Max Act: 3.0044. Min Act: -0.0000

Data Index: 156861 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 5.6224. Min Range: -5.6224

Max Act: 3.3772. Min Act: -0.0000

Data Index: 624762 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 5.6224. Min Range: -5.6224

Max Act: 3.2958. Min Act: -0.0000

Data Index: 749776 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 5.6224. Min Range: -5.6224

Max Act: 3.2045. Min Act: -0.0000

Data Index: 467075 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 5.6224. Min Range: -5.6224

Max Act: 2.8666. Min Act: -0.0000

Data Index: 419255 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 5.6224. Min Range: -5.6224

Max Act: 3.0006. Min Act: -0.0000

Data Index: 575112 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 5.6224. Min Range: -5.6224

Max Act: 2.7752. Min Act: -0.0000

Data Index: 430755 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 5.6224. Min Range: -5.6224

Max Act: 2.9598. Min Act: -0.0000

Data Index: 811819 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 5.6224. Min Range: -5.6224

Max Act: 2.5357. Min Act: -0.0000

Data Index: 876437 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 5.6224. Min Range: -5.6224

Max Act: 2.8926. Min Act: -0.0000

Data Index: 926724 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 5.6224. Min Range: -5.6224

Max Act: 2.9708. Min Act: -0.0000

Data Index: 276781 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 5.6224. Min Range: -5.6224

Max Act: 2.8281. Min Act: -0.0000

Data Index: 61774 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 5.6224. Min Range: -5.6224

Max Act: 2.8125. Min Act: -0.0000

Data Index: 681048 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 5.6224. Min Range: -5.6224

Max Act: 2.9289. Min Act: -0.0000

Data Index: 362748 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 5.6224. Min Range: -5.6224

Max Act: 2.6399. Min Act: -0.0000

Data Index: 507641 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 5.6224. Min Range: -5.6224

Max Act: 2.6364. Min Act: -0.0000

Data Index: 826939 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 5.6224. Min Range: -5.6224

Max Act: 2.7684. Min Act: -0.0000

Data Index: 510512 (C4 (Web Text))

Max Activating Token Index: 96