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

Dataset: The Pile

Neuron 2800 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.2181. Min Act: -0.0000

Data Index: 1462216 (The Pile)

Max Activating Token Index: 169

Text #1

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.1933. Min Act: -0.0000

Data Index: 103510 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1956866 (The Pile)

Max Activating Token Index: 18

Text #3

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8620. Min Act: -0.0000

Data Index: 634511 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1838370 (The Pile)

Max Activating Token Index: 915

Text #5

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1247447 (The Pile)

Max Activating Token Index: 47

Text #6

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1999994 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7783. Min Act: -0.0000

Data Index: 530961 (The Pile)

Max Activating Token Index: 719

Text #8

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7438. Min Act: -0.0000

Data Index: 518797 (The Pile)

Max Activating Token Index: 628

Text #9

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1616335 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1143798 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1283176 (The Pile)

Max Activating Token Index: 534

Text #12

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7028. Min Act: -0.0000

Data Index: 882121 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7169. Min Act: -0.0000

Data Index: 897616 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.6928. Min Act: -0.0000

Data Index: 587682 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1774562 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1590738 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1836067 (The Pile)

Max Activating Token Index: 353

Text #18

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.6909. Min Act: -0.0000

Data Index: 1142256 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1895840 (The Pile)

Max Activating Token Index: 453