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

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

Neuron 3457 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4912. Min Act: -0.0000

Data Index: 460792 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4768. Min Act: -0.0000

Data Index: 940724 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4283. Min Act: -0.0000

Data Index: 413116 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4185. Min Act: -0.0000

Data Index: 1219927 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.3637. Min Act: -0.0000

Data Index: 1321126 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.3689. Min Act: -0.0000

Data Index: 1284997 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.3852. Min Act: -0.0000

Data Index: 567208 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.3994. Min Act: -0.0000

Data Index: 167291 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1163631 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.3261. Min Act: -0.0000

Data Index: 805177 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.3589. Min Act: -0.0000

Data Index: 159768 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.2469. Min Act: -0.0000

Data Index: 704587 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.3256. Min Act: -0.0000

Data Index: 958002 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.3150. Min Act: -0.0000

Data Index: 1230224 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.2419. Min Act: -0.0000

Data Index: 168990 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.3549. Min Act: -0.0000

Data Index: 821577 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.2731. Min Act: -0.0000

Data Index: 202504 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.2306. Min Act: -0.0000

Data Index: 1134805 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.3571. Min Act: -0.0000

Data Index: 289257 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.2665. Min Act: -0.0000

Data Index: 617633 (C4 (Web Text))

Max Activating Token Index: 503