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

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

Neuron 3384 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: 1.8638. Min Range: -1.8638

Max Act: 1.8638. Min Act: -0.0000

Data Index: 107002 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.7862. Min Act: -0.0000

Data Index: 283078 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.6525. Min Act: -0.0000

Data Index: 170316 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.6296. Min Act: -0.0000

Data Index: 874783 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.6671. Min Act: -0.0000

Data Index: 1081779 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.5702. Min Act: -0.0000

Data Index: 384775 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.6070. Min Act: -0.0000

Data Index: 1205101 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.6369. Min Act: -0.0000

Data Index: 177719 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.4946. Min Act: -0.0000

Data Index: 1009152 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.5377. Min Act: -0.0000

Data Index: 464060 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.5415. Min Act: -0.0000

Data Index: 899559 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.5269. Min Act: -0.0000

Data Index: 847767 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.6177. Min Act: -0.0000

Data Index: 57430 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.4646. Min Act: -0.0000

Data Index: 1516358 (Python Code)

Max Activating Token Index: 247

Text #14

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.4290. Min Act: -0.0000

Data Index: 1021824 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.4496. Min Act: -0.0000

Data Index: 910017 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.4712. Min Act: -0.0000

Data Index: 1291126 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.5444. Min Act: -0.0000

Data Index: 188496 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.4332. Min Act: -0.0000

Data Index: 1105347 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 1.8638. Min Range: -1.8638

Max Act: 1.4275. Min Act: -0.0001

Data Index: 774008 (C4 (Web Text))

Max Activating Token Index: 115