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

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

Neuron 3770 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.1242. Min Act: -0.0000

Data Index: 113456 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.1387. Min Act: -0.0000

Data Index: 584500 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.1634. Min Act: -0.0000

Data Index: 154187 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.2333. Min Act: -0.0000

Data Index: 912989 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9802. Min Act: -0.0000

Data Index: 101545 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9392. Min Act: -0.0000

Data Index: 853367 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1305285 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.0270. Min Act: -0.0000

Data Index: 741421 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9550. Min Act: -0.0000

Data Index: 427668 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.8945. Min Act: -0.0000

Data Index: 221606 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.8697. Min Act: -0.0000

Data Index: 893463 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1183303 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9021. Min Act: -0.0000

Data Index: 795692 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9114. Min Act: -0.0000

Data Index: 155119 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9098. Min Act: -0.0000

Data Index: 621819 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9427. Min Act: -0.0000

Data Index: 596210 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1309690 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9226. Min Act: -0.0000

Data Index: 80142 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9089. Min Act: -0.0000

Data Index: 201365 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.8785. Min Act: -0.0000

Data Index: 400746 (C4 (Web Text))

Max Activating Token Index: 588