Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 407 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1683163 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2825. Min Act: -0.0000

Data Index: 1744699 (The Pile)

Max Activating Token Index: 525

Text #2

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1015029 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2489. Min Act: -0.0000

Data Index: 541213 (The Pile)

Max Activating Token Index: 521

Text #4

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2413. Min Act: -0.0000

Data Index: 996099 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2553. Min Act: -0.0000

Data Index: 760037 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2374. Min Act: -0.0000

Data Index: 154177 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1974251 (The Pile)

Max Activating Token Index: 534

Text #8

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2455. Min Act: -0.0000

Data Index: 798410 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1282310 (The Pile)

Max Activating Token Index: 513

Text #10

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2453. Min Act: -0.0000

Data Index: 315384 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2433. Min Act: -0.0000

Data Index: 439767 (The Pile)

Max Activating Token Index: 97

Text #12

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2433. Min Act: -0.0000

Data Index: 939645 (The Pile)

Max Activating Token Index: 513

Text #13

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2252. Min Act: -0.0000

Data Index: 555760 (The Pile)

Max Activating Token Index: 106

Text #14

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1829108 (The Pile)

Max Activating Token Index: 872

Text #15

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2344. Min Act: -0.0000

Data Index: 203318 (The Pile)

Max Activating Token Index: 656

Text #16

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2430. Min Act: -0.0000

Data Index: 997147 (The Pile)

Max Activating Token Index: 787

Text #17

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2404. Min Act: -0.0000

Data Index: 171381 (The Pile)

Max Activating Token Index: 785

Text #18

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1432350 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1879446 (The Pile)

Max Activating Token Index: 594