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

Dataset: The Pile

Neuron 268 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3758. Min Range: -5.3758

Max Act: 5.3758. Min Act: -0.0000

Data Index: 543947 (The Pile)

Max Activating Token Index: 279

Text #1

Max Range: 5.3758. Min Range: -5.3758

Max Act: 5.2698. Min Act: -0.0000

Data Index: 1989849 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.9218. Min Act: -0.0000

Data Index: 623460 (The Pile)

Max Activating Token Index: 410

Text #3

Max Range: 5.3758. Min Range: -5.3758

Max Act: 5.2617. Min Act: -0.0000

Data Index: 1647969 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.8274. Min Act: -0.0000

Data Index: 207866 (The Pile)

Max Activating Token Index: 444

Text #5

Max Range: 5.3758. Min Range: -5.3758

Max Act: 5.0017. Min Act: -0.0000

Data Index: 350117 (The Pile)

Max Activating Token Index: 256

Text #6

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.5023. Min Act: -0.0000

Data Index: 71995 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.6232. Min Act: -0.0000

Data Index: 603675 (The Pile)

Max Activating Token Index: 272

Text #8

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.5649. Min Act: -0.0000

Data Index: 1288533 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.2288. Min Act: -0.0000

Data Index: 587782 (The Pile)

Max Activating Token Index: 190

Text #10

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.3839. Min Act: -0.0000

Data Index: 109253 (The Pile)

Max Activating Token Index: 544

Text #11

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.3593. Min Act: -0.0000

Data Index: 1400943 (The Pile)

Max Activating Token Index: 328

Text #12

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.3422. Min Act: -0.0000

Data Index: 1843777 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.2775. Min Act: -0.0000

Data Index: 531969 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.2463. Min Act: -0.0000

Data Index: 1808070 (The Pile)

Max Activating Token Index: 801

Text #15

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.2079. Min Act: -0.0000

Data Index: 1541450 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.4009. Min Act: -0.0000

Data Index: 1186032 (The Pile)

Max Activating Token Index: 821

Text #17

Max Range: 5.3758. Min Range: -5.3758

Max Act: 3.8732. Min Act: -0.0000

Data Index: 251836 (The Pile)

Max Activating Token Index: 669

Text #18

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.1630. Min Act: -0.0000

Data Index: 1325871 (The Pile)

Max Activating Token Index: 425

Text #19

Max Range: 5.3758. Min Range: -5.3758

Max Act: 4.1492. Min Act: -0.0000

Data Index: 1725144 (The Pile)

Max Activating Token Index: 159