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

Dataset: The Pile

Neuron 88 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: 1.4845. Min Range: -1.4845

Max Act: 1.4845. Min Act: -0.0000

Data Index: 82959 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3814. Min Act: -0.0000

Data Index: 1322196 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3526. Min Act: -0.0000

Data Index: 1219873 (The Pile)

Max Activating Token Index: 569

Text #3

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2615. Min Act: -0.0000

Data Index: 352088 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2544. Min Act: -0.0000

Data Index: 1707528 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1588869 (The Pile)

Max Activating Token Index: 279

Text #6

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2826. Min Act: -0.0000

Data Index: 632201 (The Pile)

Max Activating Token Index: 148

Text #7

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2107. Min Act: -0.0000

Data Index: 177726 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2521. Min Act: -0.0000

Data Index: 275505 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2529. Min Act: -0.0000

Data Index: 759467 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1985827 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2002. Min Act: -0.0000

Data Index: 797092 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3075. Min Act: -0.0000

Data Index: 1963483 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1510. Min Act: -0.0000

Data Index: 1352219 (The Pile)

Max Activating Token Index: 465

Text #14

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2474. Min Act: -0.0000

Data Index: 306087 (The Pile)

Max Activating Token Index: 754

Text #15

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1344. Min Act: -0.0000

Data Index: 1469630 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.0928. Min Act: -0.0000

Data Index: 1368865 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1611. Min Act: -0.0000

Data Index: 268141 (The Pile)

Max Activating Token Index: 663

Text #18

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1537. Min Act: -0.0000

Data Index: 725253 (The Pile)

Max Activating Token Index: 877

Text #19

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.1232. Min Act: -0.0000

Data Index: 219595 (The Pile)

Max Activating Token Index: 377