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

Dataset: The Pile

Neuron 669 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.4295. Min Act: -0.0000

Data Index: 409328 (The Pile)

Max Activating Token Index: 428

Text #1

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.4599. Min Act: -0.0000

Data Index: 975614 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.1737. Min Act: -0.0000

Data Index: 489154 (The Pile)

Max Activating Token Index: 347

Text #3

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.1909. Min Act: -0.0000

Data Index: 1027853 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1547199 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.0585. Min Act: -0.0000

Data Index: 145758 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.0745. Min Act: -0.0000

Data Index: 152637 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.0944. Min Act: -0.0000

Data Index: 529766 (The Pile)

Max Activating Token Index: 453

Text #8

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1206094 (The Pile)

Max Activating Token Index: 258

Text #9

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.0956. Min Act: -0.0000

Data Index: 1784444 (The Pile)

Max Activating Token Index: 475

Text #10

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1804162 (The Pile)

Max Activating Token Index: 778

Text #11

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.0317. Min Act: -0.0000

Data Index: 12740 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 1.4599. Min Range: -1.4599

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1728172 (The Pile)

Max Activating Token Index: 248

Text #13

Max Range: 1.4599. Min Range: -1.4599

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1965803 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 1.4599. Min Range: -1.4599

Max Act: 0.9844. Min Act: -0.0000

Data Index: 218337 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1796532 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 1.4599. Min Range: -1.4599

Max Act: 0.9418. Min Act: -0.0000

Data Index: 269560 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 1.4599. Min Range: -1.4599

Max Act: 0.8571. Min Act: -0.0000

Data Index: 280294 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 1.4599. Min Range: -1.4599

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1595976 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.0157. Min Act: -0.0000

Data Index: 357794 (The Pile)

Max Activating Token Index: 219