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

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

Neuron 4187 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0772. Min Act: -0.0003

Data Index: 1246960 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0768. Min Act: -0.0003

Data Index: 612300 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0743. Min Act: -0.0002

Data Index: 471166 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0705. Min Act: -0.0003

Data Index: 970363 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0699. Min Act: -0.0003

Data Index: 983371 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0670. Min Act: -0.0003

Data Index: 960830 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0642. Min Act: -0.0003

Data Index: 202771 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0663. Min Act: -0.0003

Data Index: 123033 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0697. Min Act: -0.0003

Data Index: 599828 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0677. Min Act: -0.0003

Data Index: 549603 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0652. Min Act: -0.0003

Data Index: 535712 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0649. Min Act: -0.0002

Data Index: 279817 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1090350 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0643. Min Act: -0.0003

Data Index: 993943 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0616. Min Act: -0.0003

Data Index: 142333 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0640. Min Act: -0.0003

Data Index: 565652 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1276328 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0635. Min Act: -0.0003

Data Index: 970403 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0618. Min Act: -0.0003

Data Index: 265624 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0628. Min Act: -0.0003

Data Index: 144939 (C4 (Web Text))

Max Activating Token Index: 134