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

Dataset: The Pile

Neuron 810 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0048. Min Range: -3.0048

Max Act: 3.0048. Min Act: -0.0000

Data Index: 1804981 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.9016. Min Act: -0.0000

Data Index: 1914923 (The Pile)

Max Activating Token Index: 697

Text #2

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.2767. Min Act: -0.0000

Data Index: 23696 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.5038. Min Act: -0.0000

Data Index: 1089345 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.3559. Min Act: -0.0000

Data Index: 1067033 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.1968. Min Act: -0.0000

Data Index: 862777 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.9846. Min Act: -0.0000

Data Index: 1786852 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.0552. Min Act: -0.0000

Data Index: 1314914 (The Pile)

Max Activating Token Index: 279

Text #8

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.8250. Min Act: -0.0000

Data Index: 452598 (The Pile)

Max Activating Token Index: 592

Text #9

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.9540. Min Act: -0.0000

Data Index: 1627166 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.7902. Min Act: -0.0000

Data Index: 774798 (The Pile)

Max Activating Token Index: 872

Text #11

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.7783. Min Act: -0.0000

Data Index: 808433 (The Pile)

Max Activating Token Index: 972

Text #12

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.7214. Min Act: -0.0000

Data Index: 840896 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.8284. Min Act: -0.0000

Data Index: 1272508 (The Pile)

Max Activating Token Index: 241

Text #14

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.8653. Min Act: -0.0000

Data Index: 1124150 (The Pile)

Max Activating Token Index: 415

Text #15

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.7025. Min Act: -0.0000

Data Index: 16360 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.5566. Min Act: -0.0000

Data Index: 1076422 (The Pile)

Max Activating Token Index: 508

Text #17

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1392205 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.6136. Min Act: -0.0000

Data Index: 1257906 (The Pile)

Max Activating Token Index: 128

Text #19

Max Range: 3.0048. Min Range: -3.0048

Max Act: 1.7707. Min Act: -0.0000

Data Index: 1548565 (The Pile)

Max Activating Token Index: 689