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

Dataset: The Pile

Neuron 759 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1045617 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1390304 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1885691 (The Pile)

Max Activating Token Index: 212

Text #3

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4644. Min Act: -0.0000

Data Index: 747850 (The Pile)

Max Activating Token Index: 243

Text #4

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1208102 (The Pile)

Max Activating Token Index: 36

Text #5

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1499500 (The Pile)

Max Activating Token Index: 393

Text #6

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1704799 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4350. Min Act: -0.0000

Data Index: 869570 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4570. Min Act: -0.0000

Data Index: 210724 (The Pile)

Max Activating Token Index: 334

Text #9

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1669338 (The Pile)

Max Activating Token Index: 726

Text #10

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3666. Min Act: -0.0000

Data Index: 201050 (The Pile)

Max Activating Token Index: 926

Text #11

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1802937 (The Pile)

Max Activating Token Index: 773

Text #12

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1185164 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1724260 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1210598 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1894024 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3725. Min Act: -0.0000

Data Index: 790371 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3869. Min Act: -0.0000

Data Index: 523853 (The Pile)

Max Activating Token Index: 928

Text #18

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3682. Min Act: -0.0000

Data Index: 560757 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1121335 (The Pile)

Max Activating Token Index: 773