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

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

Neuron 2273 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.8481. Min Act: -0.0000

Data Index: 1484035 (Python Code)

Max Activating Token Index: 977

Text #1

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.6411. Min Act: -0.0000

Data Index: 1485004 (Python Code)

Max Activating Token Index: 215

Text #2

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.5878. Min Act: -0.0000

Data Index: 1518094 (Python Code)

Max Activating Token Index: 429

Text #3

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.5563. Min Act: -0.0000

Data Index: 1549581 (Python Code)

Max Activating Token Index: 451

Text #4

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.3890. Min Act: -0.0000

Data Index: 1538278 (Python Code)

Max Activating Token Index: 267

Text #5

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.3833. Min Act: -0.0000

Data Index: 1381433 (Python Code)

Max Activating Token Index: 874

Text #6

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.2830. Min Act: -0.0000

Data Index: 1450496 (Python Code)

Max Activating Token Index: 873

Text #7

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.3335. Min Act: -0.0000

Data Index: 1615543 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.2459. Min Act: -0.0000

Data Index: 1516729 (Python Code)

Max Activating Token Index: 872

Text #9

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1586569 (Python Code)

Max Activating Token Index: 970

Text #10

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.2801. Min Act: 0.0000

Data Index: 1612382 (Python Code)

Max Activating Token Index: 142

Text #11

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.4299. Min Act: 0.0000

Data Index: 1561250 (Python Code)

Max Activating Token Index: 826

Text #12

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1560074 (Python Code)

Max Activating Token Index: 820

Text #13

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.2460. Min Act: -0.0000

Data Index: 1614235 (Python Code)

Max Activating Token Index: 658

Text #14

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.2503. Min Act: -0.0000

Data Index: 1611670 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.2790. Min Act: -0.0000

Data Index: 1454648 (Python Code)

Max Activating Token Index: 334

Text #16

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.2614. Min Act: -0.0000

Data Index: 1191893 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.2629. Min Act: -0.0000

Data Index: 1626172 (Python Code)

Max Activating Token Index: 916

Text #18

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1624363 (Python Code)

Max Activating Token Index: 856

Text #19

Max Range: 1.8481. Min Range: -1.8481

Max Act: 1.1793. Min Act: -0.0000

Data Index: 1408693 (Python Code)

Max Activating Token Index: 868