Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 635 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.5702. Min Act: -0.0002

Data Index: 364826 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.5501. Min Act: -0.0002

Data Index: 195667 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.5366. Min Act: -0.0002

Data Index: 821090 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.5269. Min Act: -0.0002

Data Index: 1229294 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.5106. Min Act: -0.0002

Data Index: 1085444 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.5198. Min Act: -0.0002

Data Index: 510658 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.5140. Min Act: -0.0002

Data Index: 744282 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4986. Min Act: -0.0002

Data Index: 462943 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4885. Min Act: -0.0002

Data Index: 525316 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4875. Min Act: -0.0002

Data Index: 1254457 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4862. Min Act: -0.0002

Data Index: 969420 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4912. Min Act: -0.0002

Data Index: 1192299 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4746. Min Act: -0.0002

Data Index: 1053837 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4843. Min Act: -0.0002

Data Index: 458311 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4845. Min Act: -0.0003

Data Index: 1095443 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4932. Min Act: -0.0002

Data Index: 1328534 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4824. Min Act: -0.0002

Data Index: 730623 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4900. Min Act: -0.0002

Data Index: 902963 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4764. Min Act: -0.0002

Data Index: 1012180 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4737. Min Act: -0.0002

Data Index: 504847 (C4 (Web Text))

Max Activating Token Index: 45