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

Dataset: The Pile

Neuron 1897 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0790. Min Range: -1.0790

Max Act: 1.0790. Min Act: -0.0000

Data Index: 1974597 (The Pile)

Max Activating Token Index: 230

Text #1

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.9995. Min Act: -0.0000

Data Index: 912199 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 1.0790. Min Range: -1.0790

Max Act: 1.0001. Min Act: -0.0000

Data Index: 38834 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.9208. Min Act: -0.0000

Data Index: 14654 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.9269. Min Act: -0.0000

Data Index: 671645 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1440875 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.9320. Min Act: -0.0000

Data Index: 1378319 (The Pile)

Max Activating Token Index: 500

Text #7

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1072412 (The Pile)

Max Activating Token Index: 900

Text #8

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1369981 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.8211. Min Act: -0.0000

Data Index: 733340 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1298261 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.9369. Min Act: -0.0000

Data Index: 329735 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.8942. Min Act: -0.0000

Data Index: 806867 (The Pile)

Max Activating Token Index: 822

Text #13

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.8392. Min Act: -0.0000

Data Index: 724711 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.8321. Min Act: -0.0000

Data Index: 322520 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.8227. Min Act: -0.0000

Data Index: 648742 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1854303 (The Pile)

Max Activating Token Index: 496

Text #17

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.7915. Min Act: -0.0000

Data Index: 525927 (The Pile)

Max Activating Token Index: 212

Text #18

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.8320. Min Act: -0.0000

Data Index: 844204 (The Pile)

Max Activating Token Index: 692

Text #19

Max Range: 1.0790. Min Range: -1.0790

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1463909 (The Pile)

Max Activating Token Index: 813