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

Dataset: The Pile

Neuron 3391 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.8456. Min Act: -0.0000

Data Index: 249859 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1455395 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6256. Min Act: 0.0000

Data Index: 1993108 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6563. Min Act: 0.0000

Data Index: 1864423 (The Pile)

Max Activating Token Index: 490

Text #4

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6437. Min Act: -0.0000

Data Index: 1108133 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1422739 (The Pile)

Max Activating Token Index: 748

Text #6

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1600931 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6301. Min Act: -0.0000

Data Index: 948378 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6084. Min Act: -0.0000

Data Index: 30668 (The Pile)

Max Activating Token Index: 462

Text #9

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5529. Min Act: 0.0000

Data Index: 413397 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5592. Min Act: -0.0000

Data Index: 173732 (The Pile)

Max Activating Token Index: 794

Text #11

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1518295 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5401. Min Act: -0.0000

Data Index: 497386 (The Pile)

Max Activating Token Index: 676

Text #13

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1924454 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1488397 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5447. Min Act: -0.0000

Data Index: 1022119 (The Pile)

Max Activating Token Index: 395

Text #16

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1596509 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1146872 (The Pile)

Max Activating Token Index: 125

Text #18

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5570. Min Act: -0.0000

Data Index: 913091 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5211. Min Act: -0.0000

Data Index: 361224 (The Pile)

Max Activating Token Index: 830