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

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

Neuron 3017 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1584105 (Python Code)

Max Activating Token Index: 509

Text #1

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1462938 (Python Code)

Max Activating Token Index: 778

Text #2

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1436454 (Python Code)

Max Activating Token Index: 718

Text #3

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3550. Min Act: -0.0000

Data Index: 965040 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3750. Min Act: -0.0000

Data Index: 1191797 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3486. Min Act: -0.0000

Data Index: 456020 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3482. Min Act: -0.0000

Data Index: 347819 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3292. Min Act: -0.0000

Data Index: 891791 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1597486 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1033024 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3140. Min Act: -0.0000

Data Index: 607414 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3309. Min Act: -0.0000

Data Index: 60403 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1586671 (Python Code)

Max Activating Token Index: 919

Text #13

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3317. Min Act: -0.0000

Data Index: 631324 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1585335 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1465850 (Python Code)

Max Activating Token Index: 921

Text #16

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1439502 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3122. Min Act: 0.0000

Data Index: 1375564 (Python Code)

Max Activating Token Index: 353

Text #18

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3011. Min Act: -0.0000

Data Index: 765420 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3086. Min Act: -0.0000

Data Index: 637710 (C4 (Web Text))

Max Activating Token Index: 189