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

Dataset: The Pile

Neuron 1010 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4913. Min Range: -7.4913

Max Act: 7.4913. Min Act: -0.0000

Data Index: 1067861 (The Pile)

Max Activating Token Index: 256

Text #1

Max Range: 7.4913. Min Range: -7.4913

Max Act: 7.0736. Min Act: -0.0000

Data Index: 1277690 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 7.4913. Min Range: -7.4913

Max Act: 6.6364. Min Act: -0.0000

Data Index: 663992 (The Pile)

Max Activating Token Index: 559

Text #3

Max Range: 7.4913. Min Range: -7.4913

Max Act: 6.3192. Min Act: -0.0000

Data Index: 1388602 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 7.4913. Min Range: -7.4913

Max Act: 7.1461. Min Act: -0.0000

Data Index: 649183 (The Pile)

Max Activating Token Index: 784

Text #5

Max Range: 7.4913. Min Range: -7.4913

Max Act: 6.5886. Min Act: -0.0000

Data Index: 1285471 (The Pile)

Max Activating Token Index: 589

Text #6

Max Range: 7.4913. Min Range: -7.4913

Max Act: 6.2871. Min Act: -0.0000

Data Index: 222713 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 7.4913. Min Range: -7.4913

Max Act: 6.0546. Min Act: -0.0000

Data Index: 1511246 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 7.4913. Min Range: -7.4913

Max Act: 5.9090. Min Act: -0.0000

Data Index: 84530 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 7.4913. Min Range: -7.4913

Max Act: 5.4333. Min Act: -0.0000

Data Index: 29042 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 7.4913. Min Range: -7.4913

Max Act: 5.5031. Min Act: -0.0000

Data Index: 73876 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 7.4913. Min Range: -7.4913

Max Act: 5.7598. Min Act: -0.0000

Data Index: 1691486 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 7.4913. Min Range: -7.4913

Max Act: 5.4981. Min Act: -0.0000

Data Index: 522764 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 7.4913. Min Range: -7.4913

Max Act: 5.0940. Min Act: -0.0000

Data Index: 1204878 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 7.4913. Min Range: -7.4913

Max Act: 5.5344. Min Act: -0.0000

Data Index: 1429300 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 7.4913. Min Range: -7.4913

Max Act: 5.4921. Min Act: -0.0000

Data Index: 653585 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 7.4913. Min Range: -7.4913

Max Act: 5.5243. Min Act: -0.0000

Data Index: 1197012 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 7.4913. Min Range: -7.4913

Max Act: 5.0896. Min Act: -0.0000

Data Index: 133097 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 7.4913. Min Range: -7.4913

Max Act: 4.6950. Min Act: -0.0000

Data Index: 1105066 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 7.4913. Min Range: -7.4913

Max Act: 4.5659. Min Act: -0.0000

Data Index: 7696 (The Pile)

Max Activating Token Index: 285