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

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

Neuron 3084 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: 2.6707. Min Range: -2.6707

Max Act: 2.6707. Min Act: -0.0000

Data Index: 1367037 (Python Code)

Max Activating Token Index: 220

Text #1

Max Range: 2.6707. Min Range: -2.6707

Max Act: 2.3986. Min Act: -0.0000

Data Index: 606493 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 2.6707. Min Range: -2.6707

Max Act: 2.1050. Min Act: -0.0000

Data Index: 429428 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.8452. Min Act: -0.0000

Data Index: 1363807 (Python Code)

Max Activating Token Index: 152

Text #4

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.9527. Min Act: -0.0000

Data Index: 1439218 (Python Code)

Max Activating Token Index: 767

Text #5

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.9062. Min Act: -0.0000

Data Index: 432366 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.7608. Min Act: -0.0000

Data Index: 1563077 (Python Code)

Max Activating Token Index: 165

Text #7

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.7732. Min Act: -0.0000

Data Index: 1441285 (Python Code)

Max Activating Token Index: 415

Text #8

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.8270. Min Act: -0.0000

Data Index: 1620262 (Python Code)

Max Activating Token Index: 312

Text #9

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.6271. Min Act: -0.0000

Data Index: 1396731 (Python Code)

Max Activating Token Index: 909

Text #10

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.5310. Min Act: -0.0000

Data Index: 1455190 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.5832. Min Act: -0.0000

Data Index: 1367349 (Python Code)

Max Activating Token Index: 180

Text #12

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.4541. Min Act: -0.0000

Data Index: 1476498 (Python Code)

Max Activating Token Index: 680

Text #13

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.5233. Min Act: -0.0000

Data Index: 105641 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.5220. Min Act: -0.0000

Data Index: 1547325 (Python Code)

Max Activating Token Index: 824

Text #15

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.5157. Min Act: -0.0000

Data Index: 1647332 (Python Code)

Max Activating Token Index: 1013

Text #16

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.4740. Min Act: -0.0000

Data Index: 157397 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.3681. Min Act: -0.0000

Data Index: 1485224 (Python Code)

Max Activating Token Index: 908

Text #18

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.3888. Min Act: -0.0000

Data Index: 1592192 (Python Code)

Max Activating Token Index: 72

Text #19

Max Range: 2.6707. Min Range: -2.6707

Max Act: 1.4678. Min Act: -0.0000

Data Index: 138441 (C4 (Web Text))

Max Activating Token Index: 746