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

Dataset: The Pile

Neuron 4236 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.6014. Min Act: -0.0000

Data Index: 1103956 (The Pile)

Max Activating Token Index: 626

Text #1

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.6033. Min Act: -0.0000

Data Index: 1584813 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.4828. Min Act: -0.0000

Data Index: 1757104 (The Pile)

Max Activating Token Index: 380

Text #3

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.1110. Min Act: -0.0000

Data Index: 1341984 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.3562. Min Act: -0.0000

Data Index: 1095570 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.2997. Min Act: -0.0000

Data Index: 702576 (The Pile)

Max Activating Token Index: 560

Text #6

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.2417. Min Act: -0.0000

Data Index: 1700952 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1927440 (The Pile)

Max Activating Token Index: 729

Text #8

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.1769. Min Act: -0.0000

Data Index: 1914982 (The Pile)

Max Activating Token Index: 696

Text #9

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.1524. Min Act: -0.0000

Data Index: 540916 (The Pile)

Max Activating Token Index: 212

Text #10

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.1367. Min Act: -0.0000

Data Index: 1510958 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1339472 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 1.6033. Min Range: -1.6033

Max Act: 1.1191. Min Act: -0.0000

Data Index: 1216457 (The Pile)

Max Activating Token Index: 203

Text #13

Max Range: 1.6033. Min Range: -1.6033

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1393012 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 1.6033. Min Range: -1.6033

Max Act: 0.8989. Min Act: -0.0000

Data Index: 972222 (The Pile)

Max Activating Token Index: 400

Text #15

Max Range: 1.6033. Min Range: -1.6033

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1491477 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 1.6033. Min Range: -1.6033

Max Act: 0.9532. Min Act: -0.0000

Data Index: 307425 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 1.6033. Min Range: -1.6033

Max Act: 0.9863. Min Act: -0.0000

Data Index: 96517 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 1.6033. Min Range: -1.6033

Max Act: 0.9827. Min Act: -0.0000

Data Index: 508494 (The Pile)

Max Activating Token Index: 360

Text #19

Max Range: 1.6033. Min Range: -1.6033

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1856772 (The Pile)

Max Activating Token Index: 995