Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 371 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.9184. Min Act: -0.0000

Data Index: 939168 (The Pile)

Max Activating Token Index: 259

Text #1

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1914484 (The Pile)

Max Activating Token Index: 963

Text #2

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.9442. Min Act: -0.0000

Data Index: 709584 (The Pile)

Max Activating Token Index: 600

Text #3

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.8226. Min Act: -0.0000

Data Index: 215187 (The Pile)

Max Activating Token Index: 704

Text #4

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.8270. Min Act: -0.0000

Data Index: 482941 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1542283 (The Pile)

Max Activating Token Index: 503

Text #6

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7913. Min Act: 0.0000

Data Index: 1373110 (The Pile)

Max Activating Token Index: 366

Text #7

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1859873 (The Pile)

Max Activating Token Index: 463

Text #8

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.8433. Min Act: -0.0000

Data Index: 459170 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.8213. Min Act: -0.0000

Data Index: 497345 (The Pile)

Max Activating Token Index: 658

Text #10

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1795845 (The Pile)

Max Activating Token Index: 602

Text #11

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.8329. Min Act: -0.0000

Data Index: 1937587 (The Pile)

Max Activating Token Index: 834

Text #12

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1433166 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1331172 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7665. Min Act: -0.0000

Data Index: 961161 (The Pile)

Max Activating Token Index: 609

Text #15

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7434. Min Act: 0.0000

Data Index: 1292209 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1777466 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1579998 (The Pile)

Max Activating Token Index: 914

Text #18

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7063. Min Act: -0.0000

Data Index: 269736 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7497. Min Act: -0.0000

Data Index: 433280 (The Pile)

Max Activating Token Index: 779