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

Dataset: The Pile

Neuron 916 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: 3.0944. Min Range: -3.0944

Max Act: 3.0944. Min Act: -0.0000

Data Index: 460644 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9114. Min Act: -0.0000

Data Index: 706547 (The Pile)

Max Activating Token Index: 693

Text #2

Max Range: 3.0944. Min Range: -3.0944

Max Act: 3.0580. Min Act: -0.0000

Data Index: 717620 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9295. Min Act: -0.0000

Data Index: 1781631 (The Pile)

Max Activating Token Index: 411

Text #4

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.7533. Min Act: -0.0000

Data Index: 1100091 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9014. Min Act: -0.0000

Data Index: 1140882 (The Pile)

Max Activating Token Index: 134

Text #6

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.7981. Min Act: -0.0000

Data Index: 961755 (The Pile)

Max Activating Token Index: 485

Text #7

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.7864. Min Act: -0.0000

Data Index: 1215545 (The Pile)

Max Activating Token Index: 630

Text #8

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.7775. Min Act: -0.0000

Data Index: 668490 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.6207. Min Act: -0.0000

Data Index: 72559 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.8697. Min Act: -0.0000

Data Index: 722206 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.7439. Min Act: -0.0000

Data Index: 1928352 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.5691. Min Act: -0.0000

Data Index: 1314454 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.5233. Min Act: -0.0000

Data Index: 1427146 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.5305. Min Act: -0.0000

Data Index: 478804 (The Pile)

Max Activating Token Index: 669

Text #15

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.6512. Min Act: -0.0000

Data Index: 1621827 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.5098. Min Act: -0.0000

Data Index: 1768765 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.6072. Min Act: -0.0000

Data Index: 688001 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.5866. Min Act: -0.0000

Data Index: 1383348 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.4266. Min Act: -0.0000

Data Index: 1891666 (The Pile)

Max Activating Token Index: 890