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

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

Neuron 4926 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.9645. Min Act: -0.0001

Data Index: 9886 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.8765. Min Act: -0.0001

Data Index: 990714 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.8301. Min Act: -0.0001

Data Index: 70659 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.6806. Min Act: -0.0001

Data Index: 834165 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.7865. Min Act: -0.0001

Data Index: 1262376 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.7033. Min Act: -0.0001

Data Index: 903462 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.7845. Min Act: -0.0001

Data Index: 1181748 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.7495. Min Act: -0.0001

Data Index: 31035 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.6457. Min Act: -0.0001

Data Index: 657705 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.5583. Min Act: -0.0001

Data Index: 9335 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.5173. Min Act: -0.0001

Data Index: 984361 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.6087. Min Act: -0.0001

Data Index: 936650 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.6126. Min Act: -0.0001

Data Index: 426838 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.3629. Min Act: -0.0001

Data Index: 524166 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.5731. Min Act: -0.0001

Data Index: 1236563 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.6459. Min Act: -0.0001

Data Index: 15436 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.5834. Min Act: -0.0001

Data Index: 385598 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.5291. Min Act: -0.0001

Data Index: 341188 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.5422. Min Act: -0.0001

Data Index: 179728 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 1.9645. Min Range: -1.9645

Max Act: 1.5604. Min Act: -0.0001

Data Index: 214841 (C4 (Web Text))

Max Activating Token Index: 201