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

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

Neuron 2950 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5549. Min Range: -3.5549

Max Act: 3.5549. Min Act: -0.0001

Data Index: 21109 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 3.5549. Min Range: -3.5549

Max Act: 3.2035. Min Act: -0.0001

Data Index: 165022 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 3.5549. Min Range: -3.5549

Max Act: 3.1595. Min Act: -0.0001

Data Index: 964101 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 3.5549. Min Range: -3.5549

Max Act: 3.1333. Min Act: -0.0001

Data Index: 142990 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 3.5549. Min Range: -3.5549

Max Act: 3.0300. Min Act: -0.0001

Data Index: 87178 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.8615. Min Act: -0.0001

Data Index: 995590 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.8603. Min Act: -0.0001

Data Index: 685672 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.8696. Min Act: -0.0000

Data Index: 46152 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.8291. Min Act: -0.0000

Data Index: 620879 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.9624. Min Act: -0.0001

Data Index: 1275743 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.6614. Min Act: -0.0001

Data Index: 125224 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.6640. Min Act: -0.0001

Data Index: 767280 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.6519. Min Act: -0.0001

Data Index: 220821 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.7590. Min Act: -0.0001

Data Index: 930680 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.9025. Min Act: -0.0001

Data Index: 761028 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.7624. Min Act: -0.0001

Data Index: 792905 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.8723. Min Act: -0.0001

Data Index: 969569 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.7073. Min Act: -0.0000

Data Index: 295155 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.7149. Min Act: -0.0001

Data Index: 1179139 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 3.5549. Min Range: -3.5549

Max Act: 2.7182. Min Act: -0.0000

Data Index: 110044 (C4 (Web Text))

Max Activating Token Index: 931