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

Dataset: The Pile

Neuron 1211 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3231. Min Act: -0.0000

Data Index: 865228 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3020. Min Act: -0.0000

Data Index: 120420 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3067. Min Act: -0.0000

Data Index: 986426 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2902. Min Act: -0.0000

Data Index: 846470 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1342234 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1136768 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1490423 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2666. Min Act: -0.0000

Data Index: 265860 (The Pile)

Max Activating Token Index: 343

Text #8

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1656787 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1233769 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1657700 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2562. Min Act: -0.0000

Data Index: 291237 (The Pile)

Max Activating Token Index: 344

Text #12

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2557. Min Act: -0.0000

Data Index: 70669 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1000315 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1860592 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2446. Min Act: -0.0000

Data Index: 361626 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2457. Min Act: -0.0000

Data Index: 114081 (The Pile)

Max Activating Token Index: 192

Text #17

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2525. Min Act: -0.0000

Data Index: 733003 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2512. Min Act: -0.0000

Data Index: 11463 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1856898 (The Pile)

Max Activating Token Index: 127