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

Dataset: The Pile

Neuron 601 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: 0.8390. Min Range: -0.8390

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1058236 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.8036. Min Act: 0.0000

Data Index: 1518548 (The Pile)

Max Activating Token Index: 755

Text #2

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.5990. Min Act: -0.0000

Data Index: 768575 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1865654 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1007958 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6540. Min Act: -0.0000

Data Index: 607902 (The Pile)

Max Activating Token Index: 517

Text #6

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1602550 (The Pile)

Max Activating Token Index: 816

Text #7

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1569080 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6203. Min Act: -0.0000

Data Index: 839767 (The Pile)

Max Activating Token Index: 982

Text #9

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1347244 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.5983. Min Act: -0.0000

Data Index: 304151 (The Pile)

Max Activating Token Index: 246

Text #11

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1067562 (The Pile)

Max Activating Token Index: 874

Text #12

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.5111. Min Act: -0.0000

Data Index: 396989 (The Pile)

Max Activating Token Index: 77

Text #13

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1658573 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.5738. Min Act: -0.0000

Data Index: 95842 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.5726. Min Act: -0.0000

Data Index: 530841 (The Pile)

Max Activating Token Index: 442

Text #16

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1715486 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.5573. Min Act: -0.0000

Data Index: 54756 (The Pile)

Max Activating Token Index: 851

Text #18

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.5147. Min Act: -0.0000

Data Index: 756489 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1036120 (The Pile)

Max Activating Token Index: 478