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

Dataset: The Pile

Neuron 1872 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2288. Min Range: -1.2288

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1318058 (The Pile)

Max Activating Token Index: 742

Text #1

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9903. Min Act: -0.0000

Data Index: 408375 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1630289 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9136. Min Act: -0.0000

Data Index: 407825 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9546. Min Act: 0.0000

Data Index: 1807914 (The Pile)

Max Activating Token Index: 94

Text #5

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9243. Min Act: -0.0000

Data Index: 635692 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1952092 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1344772 (The Pile)

Max Activating Token Index: 448

Text #8

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1576808 (The Pile)

Max Activating Token Index: 9

Text #9

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1958399 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1936344 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8868. Min Act: 0.0000

Data Index: 1349507 (The Pile)

Max Activating Token Index: 186

Text #12

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1247987 (The Pile)

Max Activating Token Index: 1017

Text #13

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7903. Min Act: 0.0000

Data Index: 232653 (The Pile)

Max Activating Token Index: 37

Text #14

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8384. Min Act: -0.0000

Data Index: 195861 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8592. Min Act: 0.0000

Data Index: 1714781 (The Pile)

Max Activating Token Index: 138

Text #16

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1035003 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8531. Min Act: -0.0000

Data Index: 167340 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8995. Min Act: -0.0000

Data Index: 567385 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1273406 (The Pile)

Max Activating Token Index: 509