Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4479 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.3213. Min Act: -0.0000

Data Index: 444472 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.9645. Min Act: -0.0000

Data Index: 1434852 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.9525. Min Act: -0.0000

Data Index: 559502 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.8244. Min Act: -0.0000

Data Index: 209209 (The Pile)

Max Activating Token Index: 28

Text #4

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.7954. Min Act: -0.0000

Data Index: 484876 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.5371. Min Act: -0.0000

Data Index: 1128433 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.0162. Min Act: -0.0000

Data Index: 1056526 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.7912. Min Act: -0.0000

Data Index: 1564163 (The Pile)

Max Activating Token Index: 840

Text #8

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.4473. Min Act: -0.0000

Data Index: 1199682 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.7436. Min Act: -0.0000

Data Index: 1034836 (The Pile)

Max Activating Token Index: 595

Text #10

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.3993. Min Act: -0.0000

Data Index: 1977876 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.7327. Min Act: -0.0000

Data Index: 1420088 (The Pile)

Max Activating Token Index: 711

Text #12

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.6482. Min Act: -0.0000

Data Index: 845646 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.3153. Min Act: -0.0000

Data Index: 1151395 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.4087. Min Act: -0.0000

Data Index: 1389584 (The Pile)

Max Activating Token Index: 636

Text #15

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.1364. Min Act: -0.0000

Data Index: 1813324 (The Pile)

Max Activating Token Index: 901

Text #16

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.3049. Min Act: -0.0000

Data Index: 236505 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.3428. Min Act: -0.0000

Data Index: 274333 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.2583. Min Act: -0.0000

Data Index: 1422358 (The Pile)

Max Activating Token Index: 896

Text #19

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.5686. Min Act: -0.0000

Data Index: 1318732 (The Pile)

Max Activating Token Index: 537