Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3074 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2334. Min Range: -1.2334

Max Act: 1.2334. Min Act: -0.0000

Data Index: 54453 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.8567. Min Act: -0.0000

Data Index: 309877 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.8076. Min Act: -0.0000

Data Index: 773051 (The Pile)

Max Activating Token Index: 393

Text #3

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1024887 (The Pile)

Max Activating Token Index: 228

Text #4

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.6557. Min Act: -0.0000

Data Index: 810238 (The Pile)

Max Activating Token Index: 377

Text #5

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1898029 (The Pile)

Max Activating Token Index: 594

Text #6

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.6881. Min Act: -0.0000

Data Index: 806427 (The Pile)

Max Activating Token Index: 199

Text #7

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.6100. Min Act: -0.0000

Data Index: 111254 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1838510 (The Pile)

Max Activating Token Index: 406

Text #9

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1817070 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.5618. Min Act: -0.0000

Data Index: 321426 (The Pile)

Max Activating Token Index: 441

Text #11

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1341028 (The Pile)

Max Activating Token Index: 422

Text #12

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.5326. Min Act: -0.0000

Data Index: 338342 (The Pile)

Max Activating Token Index: 872

Text #13

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.5732. Min Act: -0.0000

Data Index: 197760 (The Pile)

Max Activating Token Index: 590

Text #14

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1898888 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1118572 (The Pile)

Max Activating Token Index: 800

Text #16

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.5278. Min Act: -0.0000

Data Index: 582127 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.5335. Min Act: -0.0000

Data Index: 354991 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.5284. Min Act: -0.0000

Data Index: 378794 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 1.2334. Min Range: -1.2334

Max Act: 0.5203. Min Act: -0.0000

Data Index: 274166 (The Pile)

Max Activating Token Index: 714