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

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

Neuron 1606 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6522. Min Act: -0.0000

Data Index: 129086 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6155. Min Act: -0.0000

Data Index: 243640 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5817. Min Act: -0.0000

Data Index: 674187 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1133492 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5268. Min Act: -0.0000

Data Index: 97278 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5842. Min Act: -0.0000

Data Index: 555201 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4991. Min Act: -0.0000

Data Index: 961947 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5104. Min Act: -0.0000

Data Index: 534789 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4792. Min Act: -0.0000

Data Index: 964548 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4547. Min Act: -0.0000

Data Index: 750161 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4590. Min Act: -0.0000

Data Index: 118453 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1266635 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1349108 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.3857. Min Act: -0.0000

Data Index: 245858 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4108. Min Act: -0.0000

Data Index: 119016 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.3715. Min Act: -0.0000

Data Index: 298388 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1319107 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1323427 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1163943 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.3016. Min Act: -0.0000

Data Index: 752191 (C4 (Web Text))

Max Activating Token Index: 580