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

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

Neuron 838 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: 4.8763. Min Range: -4.8763

Max Act: 4.8763. Min Act: -0.0000

Data Index: 1496356 (Python Code)

Max Activating Token Index: 856

Text #1

Max Range: 4.8763. Min Range: -4.8763

Max Act: 4.8198. Min Act: -0.0000

Data Index: 1481743 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 4.8763. Min Range: -4.8763

Max Act: 4.7983. Min Act: -0.0000

Data Index: 1461262 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 4.8763. Min Range: -4.8763

Max Act: 4.2983. Min Act: -0.0000

Data Index: 1425481 (Python Code)

Max Activating Token Index: 300

Text #4

Max Range: 4.8763. Min Range: -4.8763

Max Act: 4.4500. Min Act: -0.0000

Data Index: 1624248 (Python Code)

Max Activating Token Index: 185

Text #5

Max Range: 4.8763. Min Range: -4.8763

Max Act: 4.0421. Min Act: -0.0000

Data Index: 1576086 (Python Code)

Max Activating Token Index: 354

Text #6

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.6238. Min Act: -0.0000

Data Index: 1534303 (Python Code)

Max Activating Token Index: 538

Text #7

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.7710. Min Act: -0.0000

Data Index: 1434235 (Python Code)

Max Activating Token Index: 995

Text #8

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.5857. Min Act: -0.0000

Data Index: 1640490 (Python Code)

Max Activating Token Index: 348

Text #9

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.7142. Min Act: -0.0000

Data Index: 1551574 (Python Code)

Max Activating Token Index: 904

Text #10

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.5084. Min Act: -0.0000

Data Index: 1528545 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.8351. Min Act: -0.0000

Data Index: 1470967 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.5710. Min Act: -0.0000

Data Index: 1409461 (Python Code)

Max Activating Token Index: 899

Text #13

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.5982. Min Act: -0.0000

Data Index: 1490740 (Python Code)

Max Activating Token Index: 508

Text #14

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.5654. Min Act: -0.0000

Data Index: 1475408 (Python Code)

Max Activating Token Index: 635

Text #15

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.5396. Min Act: -0.0000

Data Index: 1435303 (Python Code)

Max Activating Token Index: 173

Text #16

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.4834. Min Act: -0.0000

Data Index: 1528643 (Python Code)

Max Activating Token Index: 527

Text #17

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.4948. Min Act: -0.0000

Data Index: 1378284 (Python Code)

Max Activating Token Index: 502

Text #18

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.4827. Min Act: -0.0000

Data Index: 1379665 (Python Code)

Max Activating Token Index: 688

Text #19

Max Range: 4.8763. Min Range: -4.8763

Max Act: 3.4781. Min Act: -0.0000

Data Index: 1489953 (Python Code)

Max Activating Token Index: 1006