Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3117 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0276. Min Range: -2.0276

Max Act: 2.0276. Min Act: -0.0000

Data Index: 330071 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 2.0276. Min Range: -2.0276

Max Act: 1.8202. Min Act: -0.0000

Data Index: 650765 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 2.0276. Min Range: -2.0276

Max Act: 1.9063. Min Act: -0.0000

Data Index: 193626 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 2.0276. Min Range: -2.0276

Max Act: 1.7011. Min Act: -0.0000

Data Index: 697724 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 2.0276. Min Range: -2.0276

Max Act: 1.6870. Min Act: -0.0000

Data Index: 1111263 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 2.0276. Min Range: -2.0276

Max Act: 1.1273. Min Act: -0.0000

Data Index: 446466 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 2.0276. Min Range: -2.0276

Max Act: 1.0108. Min Act: -0.0000

Data Index: 114995 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 2.0276. Min Range: -2.0276

Max Act: 0.9941. Min Act: -0.0000

Data Index: 1290882 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 2.0276. Min Range: -2.0276

Max Act: 1.0229. Min Act: -0.0000

Data Index: 173866 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 2.0276. Min Range: -2.0276

Max Act: 1.0110. Min Act: -0.0000

Data Index: 641008 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 2.0276. Min Range: -2.0276

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1630552 (Python Code)

Max Activating Token Index: 219

Text #11

Max Range: 2.0276. Min Range: -2.0276

Max Act: 1.0110. Min Act: -0.0000

Data Index: 337643 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 2.0276. Min Range: -2.0276

Max Act: 0.9787. Min Act: 0.0001

Data Index: 192723 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 2.0276. Min Range: -2.0276

Max Act: 0.9588. Min Act: -0.0000

Data Index: 827553 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 2.0276. Min Range: -2.0276

Max Act: 0.9591. Min Act: -0.0000

Data Index: 612298 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 2.0276. Min Range: -2.0276

Max Act: 0.9840. Min Act: -0.0000

Data Index: 395188 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 2.0276. Min Range: -2.0276

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1417286 (Python Code)

Max Activating Token Index: 326

Text #17

Max Range: 2.0276. Min Range: -2.0276

Max Act: 0.9370. Min Act: -0.0000

Data Index: 807441 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 2.0276. Min Range: -2.0276

Max Act: 0.9282. Min Act: -0.0000

Data Index: 531439 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 2.0276. Min Range: -2.0276

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1295037 (C4 (Web Text))

Max Activating Token Index: 423