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

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

Neuron 2736 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1185186 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0615. Min Act: -0.0000

Data Index: 635214 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1343643 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1422451 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1344722 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0498. Min Act: -0.0000

Data Index: 631975 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0534. Min Act: -0.0000

Data Index: 586778 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1345110 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0491. Min Act: -0.0000

Data Index: 82547 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0453. Min Act: -0.0000

Data Index: 220130 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0467. Min Act: -0.0000

Data Index: 661203 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1185013 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0458. Min Act: -0.0000

Data Index: 611728 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0469. Min Act: -0.0000

Data Index: 597694 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0486. Min Act: -0.0000

Data Index: 757200 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0454. Min Act: -0.0000

Data Index: 786871 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0408. Min Act: -0.0000

Data Index: 1117937 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0469. Min Act: -0.0000

Data Index: 538421 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0441. Min Act: -0.0000

Data Index: 1305635 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0440. Min Act: -0.0000

Data Index: 144865 (C4 (Web Text))

Max Activating Token Index: 840