Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3964 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.2876. Min Act: -0.0000

Data Index: 170299 (The Pile)

Max Activating Token Index: 848

Text #1

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.2785. Min Act: -0.0000

Data Index: 1691831 (The Pile)

Max Activating Token Index: 96

Text #2

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3925. Min Act: -0.0000

Data Index: 507511 (The Pile)

Max Activating Token Index: 579

Text #3

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.1750. Min Act: -0.0000

Data Index: 520889 (The Pile)

Max Activating Token Index: 323

Text #4

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.1872. Min Act: -0.0000

Data Index: 1060733 (The Pile)

Max Activating Token Index: 625

Text #5

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3231. Min Act: -0.0000

Data Index: 194658 (The Pile)

Max Activating Token Index: 794

Text #6

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.2095. Min Act: -0.0000

Data Index: 270841 (The Pile)

Max Activating Token Index: 132

Text #7

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.2727. Min Act: -0.0000

Data Index: 1992977 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.2664. Min Act: -0.0000

Data Index: 1183438 (The Pile)

Max Activating Token Index: 565

Text #9

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.2006. Min Act: -0.0000

Data Index: 40714 (The Pile)

Max Activating Token Index: 255

Text #10

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.2499. Min Act: -0.0000

Data Index: 373053 (The Pile)

Max Activating Token Index: 7

Text #11

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1525167 (The Pile)

Max Activating Token Index: 435

Text #12

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.1557. Min Act: -0.0000

Data Index: 89153 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.1866. Min Act: -0.0000

Data Index: 587638 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.1882. Min Act: -0.0000

Data Index: 393299 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.1537. Min Act: -0.0000

Data Index: 355534 (The Pile)

Max Activating Token Index: 78

Text #16

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.0489. Min Act: -0.0000

Data Index: 611629 (The Pile)

Max Activating Token Index: 783

Text #17

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.2749. Min Act: -0.0000

Data Index: 449946 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.1533. Min Act: -0.0000

Data Index: 656479 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1013426 (The Pile)

Max Activating Token Index: 67