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

Dataset: The Pile

Neuron 1796 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: 0.3180. Min Range: -0.3180

Max Act: 0.3151. Min Act: -0.0000

Data Index: 630426 (The Pile)

Max Activating Token Index: 909

Text #1

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2813. Min Act: -0.0000

Data Index: 656960 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1788077 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1650998 (The Pile)

Max Activating Token Index: 336

Text #4

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1560809 (The Pile)

Max Activating Token Index: 185

Text #5

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1824262 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.3152. Min Act: -0.0000

Data Index: 649798 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1185767 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2626. Min Act: -0.0000

Data Index: 581918 (The Pile)

Max Activating Token Index: 604

Text #9

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1265016 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1495983 (The Pile)

Max Activating Token Index: 846

Text #11

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2797. Min Act: -0.0000

Data Index: 543808 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2885. Min Act: -0.0000

Data Index: 393196 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1142720 (The Pile)

Max Activating Token Index: 1014

Text #14

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2723. Min Act: -0.0000

Data Index: 210711 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1745937 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1521953 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2694. Min Act: -0.0000

Data Index: 105534 (The Pile)

Max Activating Token Index: 341

Text #18

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2611. Min Act: -0.0000

Data Index: 1430217 (The Pile)

Max Activating Token Index: 151

Text #19

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1486482 (The Pile)

Max Activating Token Index: 158