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

Dataset: The Pile

Neuron 3913 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.8365. Min Act: -0.0000

Data Index: 1172853 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 3.2827. Min Range: -3.2827

Max Act: 3.2827. Min Act: -0.0000

Data Index: 1231493 (The Pile)

Max Activating Token Index: 125

Text #2

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.4314. Min Act: -0.0000

Data Index: 139337 (The Pile)

Max Activating Token Index: 908

Text #3

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.4844. Min Act: -0.0000

Data Index: 306663 (The Pile)

Max Activating Token Index: 972

Text #4

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.4346. Min Act: -0.0000

Data Index: 522734 (The Pile)

Max Activating Token Index: 415

Text #5

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.2875. Min Act: -0.0000

Data Index: 824391 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.5250. Min Act: -0.0000

Data Index: 837614 (The Pile)

Max Activating Token Index: 968

Text #7

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.3333. Min Act: -0.0000

Data Index: 981791 (The Pile)

Max Activating Token Index: 751

Text #8

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.2376. Min Act: -0.0000

Data Index: 73964 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.2296. Min Act: -0.0000

Data Index: 285749 (The Pile)

Max Activating Token Index: 56

Text #10

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.3269. Min Act: -0.0000

Data Index: 533059 (The Pile)

Max Activating Token Index: 551

Text #11

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.2209. Min Act: -0.0000

Data Index: 218199 (The Pile)

Max Activating Token Index: 496

Text #12

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.3345. Min Act: -0.0000

Data Index: 1751505 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.1485. Min Act: -0.0000

Data Index: 1039498 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.1487. Min Act: -0.0000

Data Index: 45893 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.2464. Min Act: -0.0000

Data Index: 1295791 (The Pile)

Max Activating Token Index: 258

Text #16

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.0365. Min Act: -0.0000

Data Index: 520704 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.2669. Min Act: -0.0000

Data Index: 566014 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 3.2827. Min Range: -3.2827

Max Act: 2.1329. Min Act: -0.0000

Data Index: 1436282 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 3.2827. Min Range: -3.2827

Max Act: 1.8963. Min Act: -0.0000

Data Index: 473182 (The Pile)

Max Activating Token Index: 581