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

Dataset: The Pile

Neuron 4872 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0028. Min Range: -3.0028

Max Act: 3.0028. Min Act: -0.0000

Data Index: 1697165 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.5188. Min Act: -0.0000

Data Index: 967836 (The Pile)

Max Activating Token Index: 666

Text #2

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.6205. Min Act: -0.0000

Data Index: 1138405 (The Pile)

Max Activating Token Index: 542

Text #3

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.2938. Min Act: -0.0000

Data Index: 1716712 (The Pile)

Max Activating Token Index: 560

Text #4

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.5107. Min Act: -0.0000

Data Index: 624587 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.4788. Min Act: -0.0000

Data Index: 728205 (The Pile)

Max Activating Token Index: 268

Text #6

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.2824. Min Act: -0.0000

Data Index: 1809812 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.4003. Min Act: -0.0000

Data Index: 213555 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.3421. Min Act: -0.0000

Data Index: 354441 (The Pile)

Max Activating Token Index: 238

Text #9

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.3390. Min Act: -0.0000

Data Index: 1508993 (The Pile)

Max Activating Token Index: 556

Text #10

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.0997. Min Act: -0.0000

Data Index: 1615197 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.0901. Min Act: -0.0000

Data Index: 1616030 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.1494. Min Act: -0.0000

Data Index: 362546 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.1202. Min Act: -0.0000

Data Index: 936888 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 3.0028. Min Range: -3.0028

Max Act: 1.8178. Min Act: -0.0000

Data Index: 858387 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.1179. Min Act: -0.0000

Data Index: 1221682 (The Pile)

Max Activating Token Index: 916

Text #16

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.0494. Min Act: -0.0000

Data Index: 560651 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.1675. Min Act: -0.0000

Data Index: 733655 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.1124. Min Act: -0.0000

Data Index: 1223554 (The Pile)

Max Activating Token Index: 914

Text #19

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.0249. Min Act: -0.0000

Data Index: 1383504 (The Pile)

Max Activating Token Index: 77