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

Dataset: The Pile

Neuron 1220 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.8670. Min Act: -0.0000

Data Index: 869892 (The Pile)

Max Activating Token Index: 152

Text #1

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1655349 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1304486 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1719512 (The Pile)

Max Activating Token Index: 304

Text #4

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.7335. Min Act: -0.0000

Data Index: 1290469 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1558124 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.7130. Min Act: -0.0000

Data Index: 19115 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1157091 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1313823 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6795. Min Act: -0.0000

Data Index: 572324 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1478585 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6384. Min Act: -0.0000

Data Index: 1715598 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6047. Min Act: -0.0000

Data Index: 185449 (The Pile)

Max Activating Token Index: 719

Text #13

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6476. Min Act: -0.0000

Data Index: 41851 (The Pile)

Max Activating Token Index: 615

Text #14

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6709. Min Act: -0.0000

Data Index: 918646 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1028018 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6075. Min Act: -0.0000

Data Index: 25174 (The Pile)

Max Activating Token Index: 588

Text #17

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1895454 (The Pile)

Max Activating Token Index: 974

Text #18

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1649320 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6215. Min Act: -0.0000

Data Index: 423374 (The Pile)

Max Activating Token Index: 108