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

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

Neuron 5105 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2186. Min Range: -2.2186

Max Act: 2.2186. Min Act: -0.0000

Data Index: 1301826 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 2.2186. Min Range: -2.2186

Max Act: 2.1457. Min Act: -0.0000

Data Index: 434631 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.9053. Min Act: -0.0000

Data Index: 463319 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.6588. Min Act: -0.0000

Data Index: 861783 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.7550. Min Act: -0.0000

Data Index: 414736 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.3483. Min Act: -0.0000

Data Index: 1167917 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.4292. Min Act: -0.0000

Data Index: 247355 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.2032. Min Act: -0.0000

Data Index: 100860 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1114406 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.2412. Min Act: -0.0000

Data Index: 45548 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1046241 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.1885. Min Act: -0.0000

Data Index: 843488 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1629313 (Python Code)

Max Activating Token Index: 888

Text #13

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.1735. Min Act: -0.0000

Data Index: 65521 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1060235 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.1880. Min Act: -0.0000

Data Index: 121605 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.2501. Min Act: -0.0000

Data Index: 632100 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.2134. Min Act: -0.0000

Data Index: 597850 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.1017. Min Act: -0.0000

Data Index: 487739 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 2.2186. Min Range: -2.2186

Max Act: 1.1679. Min Act: -0.0000

Data Index: 1142468 (C4 (Web Text))

Max Activating Token Index: 711