Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3782 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.5299. Min Act: -0.0001

Data Index: 1643139 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4609. Min Act: -0.0001

Data Index: 1470165 (Python Code)

Max Activating Token Index: 551

Text #2

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4585. Min Act: -0.0001

Data Index: 1644884 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4583. Min Act: -0.0001

Data Index: 1602981 (Python Code)

Max Activating Token Index: 862

Text #4

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4551. Min Act: -0.0001

Data Index: 1598856 (Python Code)

Max Activating Token Index: 205

Text #5

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4521. Min Act: -0.0001

Data Index: 1602714 (Python Code)

Max Activating Token Index: 889

Text #6

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4300. Min Act: -0.0001

Data Index: 1491592 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1401115 (Python Code)

Max Activating Token Index: 426

Text #8

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4585. Min Act: -0.0001

Data Index: 1380299 (Python Code)

Max Activating Token Index: 575

Text #9

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1540861 (Python Code)

Max Activating Token Index: 759

Text #10

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4189. Min Act: -0.0001

Data Index: 1615765 (Python Code)

Max Activating Token Index: 769

Text #11

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1564437 (Python Code)

Max Activating Token Index: 886

Text #12

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4236. Min Act: -0.0001

Data Index: 1557756 (Python Code)

Max Activating Token Index: 514

Text #13

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4316. Min Act: -0.0001

Data Index: 1607193 (Python Code)

Max Activating Token Index: 712

Text #14

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1395172 (Python Code)

Max Activating Token Index: 889

Text #15

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1446700 (Python Code)

Max Activating Token Index: 756

Text #16

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4125. Min Act: -0.0001

Data Index: 1374372 (Python Code)

Max Activating Token Index: 964

Text #17

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1362102 (Python Code)

Max Activating Token Index: 729

Text #18

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1630595 (Python Code)

Max Activating Token Index: 895

Text #19

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.3772. Min Act: -0.0001

Data Index: 1569835 (Python Code)

Max Activating Token Index: 523