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

Dataset: The Pile

Neuron 1899 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6774. Min Range: -3.6774

Max Act: 3.5015. Min Act: -0.0000

Data Index: 622105 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 3.6774. Min Range: -3.6774

Max Act: 3.3265. Min Act: -0.0000

Data Index: 716918 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 3.6774. Min Range: -3.6774

Max Act: 3.3585. Min Act: -0.0000

Data Index: 998535 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 3.6774. Min Range: -3.6774

Max Act: 3.6774. Min Act: -0.0000

Data Index: 117794 (The Pile)

Max Activating Token Index: 713

Text #4

Max Range: 3.6774. Min Range: -3.6774

Max Act: 2.6733. Min Act: -0.0000

Data Index: 1716224 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 3.6774. Min Range: -3.6774

Max Act: 3.3048. Min Act: -0.0000

Data Index: 323172 (The Pile)

Max Activating Token Index: 440

Text #6

Max Range: 3.6774. Min Range: -3.6774

Max Act: 2.7042. Min Act: -0.0000

Data Index: 1499509 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 3.6774. Min Range: -3.6774

Max Act: 2.8368. Min Act: -0.0000

Data Index: 1882711 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 3.6774. Min Range: -3.6774

Max Act: 3.0671. Min Act: -0.0000

Data Index: 323340 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 3.6774. Min Range: -3.6774

Max Act: 3.0296. Min Act: -0.0000

Data Index: 1684745 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 3.6774. Min Range: -3.6774

Max Act: 2.8012. Min Act: -0.0000

Data Index: 1876351 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 3.6774. Min Range: -3.6774

Max Act: 2.9174. Min Act: -0.0000

Data Index: 639526 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 3.6774. Min Range: -3.6774

Max Act: 3.0861. Min Act: -0.0000

Data Index: 1567801 (The Pile)

Max Activating Token Index: 999

Text #13

Max Range: 3.6774. Min Range: -3.6774

Max Act: 3.2737. Min Act: -0.0000

Data Index: 1889125 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 3.6774. Min Range: -3.6774

Max Act: 3.0761. Min Act: -0.0000

Data Index: 1580033 (The Pile)

Max Activating Token Index: 911

Text #15

Max Range: 3.6774. Min Range: -3.6774

Max Act: 2.7964. Min Act: -0.0000

Data Index: 1812393 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 3.6774. Min Range: -3.6774

Max Act: 2.3211. Min Act: -0.0000

Data Index: 636773 (The Pile)

Max Activating Token Index: 790

Text #17

Max Range: 3.6774. Min Range: -3.6774

Max Act: 2.8694. Min Act: -0.0000

Data Index: 1512685 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 3.6774. Min Range: -3.6774

Max Act: 2.4446. Min Act: -0.0000

Data Index: 161410 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 3.6774. Min Range: -3.6774

Max Act: 2.6487. Min Act: -0.0000

Data Index: 164293 (The Pile)

Max Activating Token Index: 247