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

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

Neuron 2426 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: 2.1815. Min Range: -2.1815

Max Act: 2.1815. Min Act: -0.0000

Data Index: 709922 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 2.1815. Min Range: -2.1815

Max Act: 1.9382. Min Act: -0.0000

Data Index: 45689 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 2.1815. Min Range: -2.1815

Max Act: 1.4705. Min Act: -0.0000

Data Index: 359299 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 2.1815. Min Range: -2.1815

Max Act: 1.6173. Min Act: -0.0000

Data Index: 873184 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 2.1815. Min Range: -2.1815

Max Act: 1.2357. Min Act: -0.0000

Data Index: 148889 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 2.1815. Min Range: -2.1815

Max Act: 1.2994. Min Act: -0.0000

Data Index: 366360 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 2.1815. Min Range: -2.1815

Max Act: 1.1658. Min Act: -0.0000

Data Index: 374559 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.8621. Min Act: -0.0000

Data Index: 737366 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.8812. Min Act: -0.0000

Data Index: 423515 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.8710. Min Act: -0.0000

Data Index: 41817 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.6564. Min Act: -0.0000

Data Index: 460077 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.7197. Min Act: -0.0000

Data Index: 347863 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1141915 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1650360 (Python Code)

Max Activating Token Index: 914

Text #14

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.5578. Min Act: -0.0000

Data Index: 230605 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.4628. Min Act: 0.0000

Data Index: 146321 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.4896. Min Act: -0.0000

Data Index: 289921 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1578541 (Python Code)

Max Activating Token Index: 403

Text #18

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.4550. Min Act: -0.0000

Data Index: 651443 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 2.1815. Min Range: -2.1815

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1305137 (C4 (Web Text))

Max Activating Token Index: 680