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

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

Neuron 2373 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.8514. Min Act: -0.0000

Data Index: 1470798 (Python Code)

Max Activating Token Index: 320

Text #1

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.8618. Min Act: -0.0000

Data Index: 1481418 (Python Code)

Max Activating Token Index: 92

Text #2

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.5565. Min Act: -0.0000

Data Index: 1413070 (Python Code)

Max Activating Token Index: 601

Text #3

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.5257. Min Act: -0.0000

Data Index: 1633787 (Python Code)

Max Activating Token Index: 480

Text #4

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.3337. Min Act: -0.0000

Data Index: 1538323 (Python Code)

Max Activating Token Index: 747

Text #5

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.2880. Min Act: -0.0000

Data Index: 1556073 (Python Code)

Max Activating Token Index: 712

Text #6

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.2321. Min Act: -0.0000

Data Index: 1234955 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.1610. Min Act: -0.0000

Data Index: 1496802 (Python Code)

Max Activating Token Index: 303

Text #8

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.2248. Min Act: -0.0000

Data Index: 508824 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1626084 (Python Code)

Max Activating Token Index: 924

Text #10

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.1460. Min Act: -0.0000

Data Index: 1408269 (Python Code)

Max Activating Token Index: 261

Text #11

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.1403. Min Act: -0.0000

Data Index: 1380230 (Python Code)

Max Activating Token Index: 383

Text #12

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.2077. Min Act: -0.0000

Data Index: 1363012 (Python Code)

Max Activating Token Index: 290

Text #13

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1456494 (Python Code)

Max Activating Token Index: 333

Text #14

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.0357. Min Act: -0.0000

Data Index: 1580087 (Python Code)

Max Activating Token Index: 473

Text #15

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1531449 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1599329 (Python Code)

Max Activating Token Index: 95

Text #17

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.0040. Min Act: -0.0000

Data Index: 1516975 (Python Code)

Max Activating Token Index: 71

Text #18

Max Range: 1.8618. Min Range: -1.8618

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1555026 (Python Code)

Max Activating Token Index: 148

Text #19

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.0085. Min Act: 0.0000

Data Index: 1513208 (Python Code)

Max Activating Token Index: 617