Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 242 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1581393 (Python Code)

Max Activating Token Index: 262

Text #1

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1438620 (Python Code)

Max Activating Token Index: 740

Text #2

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1462168 (Python Code)

Max Activating Token Index: 257

Text #3

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1427897 (Python Code)

Max Activating Token Index: 654

Text #4

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1651026 (Python Code)

Max Activating Token Index: 392

Text #5

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1398653 (Python Code)

Max Activating Token Index: 624

Text #6

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1639650 (Python Code)

Max Activating Token Index: 673

Text #7

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1468088 (Python Code)

Max Activating Token Index: 513

Text #8

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1436621 (Python Code)

Max Activating Token Index: 573

Text #9

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1539754 (Python Code)

Max Activating Token Index: 637

Text #10

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1511736 (Python Code)

Max Activating Token Index: 883

Text #11

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1586418 (Python Code)

Max Activating Token Index: 942

Text #12

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1527782 (Python Code)

Max Activating Token Index: 89

Text #13

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1624620 (Python Code)

Max Activating Token Index: 220

Text #14

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1372128 (Python Code)

Max Activating Token Index: 123

Text #15

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1538378 (Python Code)

Max Activating Token Index: 386

Text #16

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1503549 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1480343 (Python Code)

Max Activating Token Index: 668

Text #18

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1645990 (Python Code)

Max Activating Token Index: 353

Text #19

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1408947 (Python Code)

Max Activating Token Index: 660