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

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

Neuron 2293 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: 1.1528. Min Range: -1.1528

Max Act: 1.1528. Min Act: -0.0001

Data Index: 324786 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.1528. Min Range: -1.1528

Max Act: 1.0418. Min Act: -0.0000

Data Index: 307646 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 1.1528. Min Range: -1.1528

Max Act: 1.0401. Min Act: -0.0000

Data Index: 433156 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.9237. Min Act: -0.0000

Data Index: 998268 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.9273. Min Act: -0.0000

Data Index: 937181 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.8554. Min Act: -0.0000

Data Index: 373897 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.9468. Min Act: -0.0001

Data Index: 20327 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.7969. Min Act: -0.0000

Data Index: 600731 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.7650. Min Act: -0.0001

Data Index: 130422 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.8327. Min Act: -0.0000

Data Index: 204726 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1167836 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.7750. Min Act: -0.0001

Data Index: 973347 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.7877. Min Act: -0.0000

Data Index: 629689 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.7335. Min Act: -0.0001

Data Index: 494169 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.7611. Min Act: -0.0000

Data Index: 1055137 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1101501 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.8346. Min Act: -0.0000

Data Index: 967392 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1269590 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1154972 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 1.1528. Min Range: -1.1528

Max Act: 0.8058. Min Act: -0.0000

Data Index: 348554 (C4 (Web Text))

Max Activating Token Index: 315