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

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

Neuron 5239 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0570. Min Act: -0.0001

Data Index: 89367 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0614. Min Act: -0.0001

Data Index: 262632 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0506. Min Act: -0.0001

Data Index: 601284 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0444. Min Act: -0.0002

Data Index: 42901 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0422. Min Act: -0.0001

Data Index: 57052 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0421. Min Act: -0.0001

Data Index: 751715 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0408. Min Act: -0.0001

Data Index: 616921 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0441. Min Act: -0.0001

Data Index: 268244 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1284260 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0426. Min Act: -0.0001

Data Index: 482540 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0401. Min Act: -0.0001

Data Index: 1299319 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0418. Min Act: -0.0001

Data Index: 981809 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0394. Min Act: -0.0001

Data Index: 880735 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0412. Min Act: -0.0001

Data Index: 823617 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0424. Min Act: -0.0001

Data Index: 134427 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0422. Min Act: -0.0001

Data Index: 161335 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1088926 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1008060 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0420. Min Act: -0.0001

Data Index: 1091568 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0421. Min Act: -0.0001

Data Index: 418717 (C4 (Web Text))

Max Activating Token Index: 31