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

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

Neuron 3461 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5322. Min Range: -1.5322

Max Act: 1.5322. Min Act: -0.0000

Data Index: 1480320 (Python Code)

Max Activating Token Index: 181

Text #1

Max Range: 1.5322. Min Range: -1.5322

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1397523 (Python Code)

Max Activating Token Index: 84

Text #2

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1429974 (Python Code)

Max Activating Token Index: 780

Text #3

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.7476. Min Act: -0.0000

Data Index: 430867 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1520792 (Python Code)

Max Activating Token Index: 352

Text #5

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.6611. Min Act: -0.0000

Data Index: 814486 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1583522 (Python Code)

Max Activating Token Index: 277

Text #7

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1413783 (Python Code)

Max Activating Token Index: 759

Text #8

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1037836 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1639608 (Python Code)

Max Activating Token Index: 947

Text #10

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1655773 (Python Code)

Max Activating Token Index: 367

Text #11

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1529075 (Python Code)

Max Activating Token Index: 1011

Text #12

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1575292 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1472496 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1607956 (Python Code)

Max Activating Token Index: 677

Text #15

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1437069 (Python Code)

Max Activating Token Index: 427

Text #16

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1396849 (Python Code)

Max Activating Token Index: 924

Text #17

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1442175 (Python Code)

Max Activating Token Index: 450

Text #18

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1554544 (Python Code)

Max Activating Token Index: 928

Text #19

Max Range: 1.5322. Min Range: -1.5322

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1499314 (Python Code)

Max Activating Token Index: 608