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

Dataset: The Pile

Neuron 2702 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1650087 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.3045. Min Act: -0.0000

Data Index: 787919 (The Pile)

Max Activating Token Index: 405

Text #2

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.3052. Min Act: -0.0000

Data Index: 1208797 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2847. Min Act: -0.0000

Data Index: 865999 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1816179 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2880. Min Act: -0.0000

Data Index: 398296 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1973815 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1207416 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1570109 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1311588 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2528. Min Act: -0.0000

Data Index: 856996 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2599. Min Act: -0.0000

Data Index: 221984 (The Pile)

Max Activating Token Index: 506

Text #12

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1710519 (The Pile)

Max Activating Token Index: 330

Text #13

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2737. Min Act: 0.0000

Data Index: 577571 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1837143 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2651. Min Act: 0.0000

Data Index: 12281 (The Pile)

Max Activating Token Index: 516

Text #16

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1717431 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2564. Min Act: -0.0000

Data Index: 802241 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1075625 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1869991 (The Pile)

Max Activating Token Index: 700