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

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

Neuron 16 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.8261. Min Act: -0.0001

Data Index: 1173545 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7599. Min Act: -0.0001

Data Index: 766866 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5932. Min Act: -0.0001

Data Index: 452058 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6211. Min Act: -0.0001

Data Index: 889248 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6190. Min Act: -0.0001

Data Index: 930616 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6541. Min Act: -0.0001

Data Index: 280188 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5723. Min Act: -0.0001

Data Index: 948062 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5688. Min Act: -0.0001

Data Index: 102442 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5804. Min Act: -0.0001

Data Index: 1114056 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6024. Min Act: -0.0001

Data Index: 917787 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5671. Min Act: -0.0001

Data Index: 401771 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5588. Min Act: -0.0001

Data Index: 1324304 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5539. Min Act: -0.0001

Data Index: 1160553 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5504. Min Act: -0.0001

Data Index: 1125365 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5393. Min Act: -0.0001

Data Index: 200506 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5653. Min Act: -0.0001

Data Index: 1145456 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5737. Min Act: -0.0001

Data Index: 5789 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5512. Min Act: -0.0001

Data Index: 13253 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5118. Min Act: -0.0001

Data Index: 83272 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5534. Min Act: -0.0001

Data Index: 1272830 (C4 (Web Text))

Max Activating Token Index: 749