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

Dataset: The Pile

Neuron 630 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.2049. Min Act: -0.0000

Data Index: 681182 (The Pile)

Max Activating Token Index: 99

Text #1

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1175146 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1196311 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1811. Min Act: -0.0000

Data Index: 883478 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1863. Min Act: -0.0000

Data Index: 638680 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1802. Min Act: 0.0000

Data Index: 1983278 (The Pile)

Max Activating Token Index: 856

Text #6

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1239507 (The Pile)

Max Activating Token Index: 707

Text #7

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1015511 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1579. Min Act: -0.0000

Data Index: 909516 (The Pile)

Max Activating Token Index: 673

Text #9

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1562. Min Act: -0.0000

Data Index: 173490 (The Pile)

Max Activating Token Index: 749

Text #10

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1036118 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1861322 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1559. Min Act: -0.0000

Data Index: 787427 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1493. Min Act: 0.0000

Data Index: 731103 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1320275 (The Pile)

Max Activating Token Index: 859

Text #15

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1462717 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1365. Min Act: -0.0000

Data Index: 92372 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1497. Min Act: -0.0000

Data Index: 1912183 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1434. Min Act: -0.0000

Data Index: 906973 (The Pile)

Max Activating Token Index: 323

Text #19

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1402. Min Act: -0.0000

Data Index: 1478938 (The Pile)

Max Activating Token Index: 178