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

Dataset: The Pile

Neuron 3207 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3788. Min Range: -3.3788

Max Act: 3.0012. Min Act: -0.0000

Data Index: 487357 (The Pile)

Max Activating Token Index: 335

Text #1

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.8620. Min Act: -0.0000

Data Index: 545822 (The Pile)

Max Activating Token Index: 551

Text #2

Max Range: 3.3788. Min Range: -3.3788

Max Act: 3.3788. Min Act: -0.0000

Data Index: 1244314 (The Pile)

Max Activating Token Index: 792

Text #3

Max Range: 3.3788. Min Range: -3.3788

Max Act: 3.0712. Min Act: -0.0000

Data Index: 822759 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 3.3788. Min Range: -3.3788

Max Act: 3.1587. Min Act: -0.0000

Data Index: 463174 (The Pile)

Max Activating Token Index: 219

Text #5

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.6671. Min Act: -0.0000

Data Index: 315822 (The Pile)

Max Activating Token Index: 180

Text #6

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.5364. Min Act: -0.0000

Data Index: 1020401 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 3.3788. Min Range: -3.3788

Max Act: 1.7822. Min Act: -0.0000

Data Index: 1460345 (The Pile)

Max Activating Token Index: 818

Text #8

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.8989. Min Act: -0.0000

Data Index: 697528 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.3441. Min Act: -0.0000

Data Index: 873386 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.7290. Min Act: -0.0000

Data Index: 94648 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.5939. Min Act: -0.0000

Data Index: 1653825 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.3595. Min Act: -0.0000

Data Index: 323395 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.2963. Min Act: -0.0000

Data Index: 177992 (The Pile)

Max Activating Token Index: 771

Text #14

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.3860. Min Act: -0.0000

Data Index: 349848 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.4614. Min Act: -0.0000

Data Index: 1327736 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.4654. Min Act: -0.0000

Data Index: 947831 (The Pile)

Max Activating Token Index: 608

Text #17

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.0140. Min Act: -0.0000

Data Index: 635424 (The Pile)

Max Activating Token Index: 379

Text #18

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.0902. Min Act: -0.0000

Data Index: 1954322 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 3.3788. Min Range: -3.3788

Max Act: 2.1838. Min Act: -0.0000

Data Index: 210774 (The Pile)

Max Activating Token Index: 142