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

Dataset: The Pile

Neuron 2651 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1828450 (The Pile)

Max Activating Token Index: 601

Text #1

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1796942 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1816986 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.4064. Min Act: -0.0000

Data Index: 875043 (The Pile)

Max Activating Token Index: 654

Text #4

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1511426 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.4164. Min Act: -0.0000

Data Index: 55208 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1246812 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3929. Min Act: -0.0000

Data Index: 446769 (The Pile)

Max Activating Token Index: 860

Text #8

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3834. Min Act: -0.0000

Data Index: 951978 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.4241. Min Act: -0.0000

Data Index: 68686 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.4216. Min Act: -0.0000

Data Index: 91553 (The Pile)

Max Activating Token Index: 229

Text #11

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3309. Min Act: -0.0000

Data Index: 484456 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3765. Min Act: -0.0000

Data Index: 1407025 (The Pile)

Max Activating Token Index: 804

Text #13

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3716. Min Act: -0.0000

Data Index: 775145 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1868298 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1520433 (The Pile)

Max Activating Token Index: 453

Text #16

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1454408 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1263514 (The Pile)

Max Activating Token Index: 566

Text #18

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3910. Min Act: -0.0000

Data Index: 497205 (The Pile)

Max Activating Token Index: 708

Text #19

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3599. Min Act: -0.0000

Data Index: 29279 (The Pile)

Max Activating Token Index: 896