Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1653 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.6655. Min Act: -0.0000

Data Index: 631535 (The Pile)

Max Activating Token Index: 693

Text #1

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.4439. Min Act: -0.0000

Data Index: 649523 (The Pile)

Max Activating Token Index: 70

Text #2

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.6076. Min Act: -0.0000

Data Index: 1464592 (The Pile)

Max Activating Token Index: 18

Text #3

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.3826. Min Act: -0.0000

Data Index: 1996804 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.9681. Min Act: -0.0000

Data Index: 604197 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.5512. Min Act: -0.0000

Data Index: 1517318 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.9869. Min Act: -0.0000

Data Index: 1037366 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.2766. Min Act: -0.0000

Data Index: 1854407 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.7386. Min Act: -0.0000

Data Index: 593737 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.2327. Min Act: -0.0000

Data Index: 1205454 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.7720. Min Act: -0.0000

Data Index: 812156 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.0417. Min Act: -0.0000

Data Index: 1791492 (The Pile)

Max Activating Token Index: 314

Text #12

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.8574. Min Act: -0.0000

Data Index: 1446263 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.4586. Min Act: -0.0000

Data Index: 1206503 (The Pile)

Max Activating Token Index: 898

Text #14

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.1212. Min Act: -0.0000

Data Index: 546159 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.9880. Min Act: -0.0000

Data Index: 1318110 (The Pile)

Max Activating Token Index: 7

Text #16

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.8511. Min Act: -0.0000

Data Index: 1479997 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.7855. Min Act: -0.0000

Data Index: 1944700 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.0722. Min Act: -0.0000

Data Index: 1563127 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.0593. Min Act: -0.0000

Data Index: 154841 (The Pile)

Max Activating Token Index: 380