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

Dataset: The Pile

Neuron 3095 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: 1.4079. Min Range: -1.4079

Max Act: 1.3408. Min Act: -0.0000

Data Index: 1173603 (The Pile)

Max Activating Token Index: 451

Text #1

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.3246. Min Act: -0.0000

Data Index: 645816 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1701148 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.2290. Min Act: -0.0000

Data Index: 201860 (The Pile)

Max Activating Token Index: 871

Text #4

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.3083. Min Act: -0.0000

Data Index: 716494 (The Pile)

Max Activating Token Index: 965

Text #5

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.4079. Min Act: -0.0000

Data Index: 381814 (The Pile)

Max Activating Token Index: 946

Text #6

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1619526 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.1650. Min Act: -0.0000

Data Index: 1893995 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.2344. Min Act: -0.0000

Data Index: 130468 (The Pile)

Max Activating Token Index: 629

Text #9

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.2063. Min Act: -0.0000

Data Index: 299600 (The Pile)

Max Activating Token Index: 794

Text #10

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.1665. Min Act: -0.0000

Data Index: 790736 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.2270. Min Act: -0.0000

Data Index: 1937490 (The Pile)

Max Activating Token Index: 14

Text #12

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1893708 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.2309. Min Act: -0.0000

Data Index: 1899219 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.2744. Min Act: -0.0000

Data Index: 1025661 (The Pile)

Max Activating Token Index: 917

Text #15

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.2269. Min Act: -0.0000

Data Index: 1526491 (The Pile)

Max Activating Token Index: 697

Text #16

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.1410. Min Act: -0.0000

Data Index: 979964 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.0859. Min Act: -0.0001

Data Index: 1630291 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.1253. Min Act: -0.0000

Data Index: 904919 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.0477. Min Act: -0.0000

Data Index: 798437 (The Pile)

Max Activating Token Index: 933