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

Dataset: The Pile

Neuron 1098 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: 1.4090. Min Range: -1.4090

Max Act: 1.4090. Min Act: -0.0000

Data Index: 99963 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1275267 (The Pile)

Max Activating Token Index: 921

Text #2

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1682. Min Act: -0.0000

Data Index: 11131 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.2596. Min Act: -0.0000

Data Index: 335786 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1377333 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1288. Min Act: -0.0000

Data Index: 1132344 (The Pile)

Max Activating Token Index: 561

Text #6

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0427. Min Act: -0.0000

Data Index: 739533 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9797. Min Act: 0.0000

Data Index: 1119721 (The Pile)

Max Activating Token Index: 68

Text #8

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9974. Min Act: -0.0000

Data Index: 373120 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8715. Min Act: -0.0000

Data Index: 531554 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0100. Min Act: -0.0000

Data Index: 1264774 (The Pile)

Max Activating Token Index: 394

Text #11

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1596362 (The Pile)

Max Activating Token Index: 588

Text #12

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1119443 (The Pile)

Max Activating Token Index: 198

Text #13

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8746. Min Act: 0.0000

Data Index: 507152 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1283109 (The Pile)

Max Activating Token Index: 390

Text #15

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8818. Min Act: -0.0000

Data Index: 24261 (The Pile)

Max Activating Token Index: 577

Text #16

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9594. Min Act: -0.0000

Data Index: 483944 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8817. Min Act: -0.0000

Data Index: 445914 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1395994 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8315. Min Act: -0.0000

Data Index: 239932 (The Pile)

Max Activating Token Index: 149