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

Dataset: The Pile

Neuron 402 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: 1.3342. Min Range: -1.3342

Max Act: 1.3342. Min Act: -0.0000

Data Index: 546168 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.1695. Min Act: -0.0000

Data Index: 990875 (The Pile)

Max Activating Token Index: 210

Text #2

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.2313. Min Act: -0.0000

Data Index: 673530 (The Pile)

Max Activating Token Index: 376

Text #3

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.1269. Min Act: -0.0000

Data Index: 11550 (The Pile)

Max Activating Token Index: 861

Text #4

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.2427. Min Act: -0.0000

Data Index: 1163917 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.0597. Min Act: -0.0000

Data Index: 129339 (The Pile)

Max Activating Token Index: 159

Text #6

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.1051. Min Act: -0.0000

Data Index: 1382528 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.2403. Min Act: -0.0000

Data Index: 194192 (The Pile)

Max Activating Token Index: 174

Text #8

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.1031. Min Act: -0.0000

Data Index: 818402 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.1535. Min Act: -0.0000

Data Index: 225577 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.1890. Min Act: -0.0000

Data Index: 1897018 (The Pile)

Max Activating Token Index: 624

Text #11

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1620700 (The Pile)

Max Activating Token Index: 597

Text #12

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.1066. Min Act: -0.0000

Data Index: 891340 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.1074. Min Act: -0.0000

Data Index: 655710 (The Pile)

Max Activating Token Index: 381

Text #14

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.0029. Min Act: -0.0000

Data Index: 1206190 (The Pile)

Max Activating Token Index: 316

Text #15

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.1523. Min Act: -0.0000

Data Index: 152525 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.1353. Min Act: -0.0000

Data Index: 79001 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.1198. Min Act: -0.0000

Data Index: 616547 (The Pile)

Max Activating Token Index: 290

Text #18

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.0572. Min Act: -0.0000

Data Index: 271619 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1126516 (The Pile)

Max Activating Token Index: 341