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

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

Neuron 1694 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0001

Data Index: 472140 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0459. Min Act: -0.0001

Data Index: 211128 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0492. Min Act: -0.0001

Data Index: 894633 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0498. Min Act: -0.0001

Data Index: 883098 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0455. Min Act: -0.0001

Data Index: 495280 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0464. Min Act: -0.0001

Data Index: 113979 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0448. Min Act: -0.0001

Data Index: 17659 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0450. Min Act: -0.0001

Data Index: 482242 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1091324 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0447. Min Act: -0.0001

Data Index: 292860 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0445. Min Act: -0.0001

Data Index: 248645 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1558967 (Python Code)

Max Activating Token Index: 231

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0397. Min Act: -0.0001

Data Index: 559800 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0400. Min Act: -0.0001

Data Index: 970328 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0403. Min Act: -0.0001

Data Index: 859363 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1054536 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1200195 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0410. Min Act: -0.0001

Data Index: 974775 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0394. Min Act: -0.0001

Data Index: 871256 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0453. Min Act: -0.0001

Data Index: 504527 (C4 (Web Text))

Max Activating Token Index: 733