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

Dataset: The Pile

Neuron 2407 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: 0.3742. Min Range: -0.3742

Max Act: 0.3734. Min Act: -0.0000

Data Index: 87370 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1181985 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3375. Min Act: -0.0000

Data Index: 98330 (The Pile)

Max Activating Token Index: 792

Text #3

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2682. Min Act: -0.0000

Data Index: 17060 (The Pile)

Max Activating Token Index: 400

Text #4

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1270515 (The Pile)

Max Activating Token Index: 672

Text #5

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1468887 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1262028 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1759992 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1538002 (The Pile)

Max Activating Token Index: 789

Text #9

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1451314 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1355671 (The Pile)

Max Activating Token Index: 882

Text #11

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1088260 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2337. Min Act: -0.0000

Data Index: 532179 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2559. Min Act: -0.0000

Data Index: 352570 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2381. Min Act: -0.0000

Data Index: 950207 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2440. Min Act: -0.0000

Data Index: 448404 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1990363 (The Pile)

Max Activating Token Index: 718

Text #17

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2198. Min Act: -0.0000

Data Index: 966850 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1086599 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1033953 (The Pile)

Max Activating Token Index: 1007