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

Dataset: The Pile

Neuron 21 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: 0.4999. Min Range: -0.4999

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1602767 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.3747. Min Act: -0.0000

Data Index: 749019 (The Pile)

Max Activating Token Index: 933

Text #2

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.3415. Min Act: -0.0000

Data Index: 923537 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1187524 (The Pile)

Max Activating Token Index: 782

Text #4

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2788. Min Act: -0.0000

Data Index: 395316 (The Pile)

Max Activating Token Index: 716

Text #5

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1991673 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1712958 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1898436 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1633922 (The Pile)

Max Activating Token Index: 513

Text #9

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2483. Min Act: -0.0000

Data Index: 638858 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2917. Min Act: -0.0000

Data Index: 968005 (The Pile)

Max Activating Token Index: 908

Text #11

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2837. Min Act: -0.0000

Data Index: 871201 (The Pile)

Max Activating Token Index: 488

Text #12

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.3096. Min Act: -0.0000

Data Index: 869902 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1887548 (The Pile)

Max Activating Token Index: 865

Text #14

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1519366 (The Pile)

Max Activating Token Index: 119

Text #15

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2502. Min Act: -0.0000

Data Index: 246116 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2638. Min Act: -0.0000

Data Index: 28079 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1177954 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2702. Min Act: -0.0000

Data Index: 707155 (The Pile)

Max Activating Token Index: 639

Text #19

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.2374. Min Act: -0.0000

Data Index: 257566 (The Pile)

Max Activating Token Index: 941