Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2602 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1580068 (The Pile)

Max Activating Token Index: 112

Text #1

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1977998 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1165101 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1974293 (The Pile)

Max Activating Token Index: 48

Text #4

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3210. Min Act: -0.0000

Data Index: 350896 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3068. Min Act: -0.0000

Data Index: 448879 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3264. Min Act: -0.0000

Data Index: 344896 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1821734 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1162540 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3073. Min Act: -0.0000

Data Index: 830902 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3077. Min Act: -0.0000

Data Index: 282243 (The Pile)

Max Activating Token Index: 87

Text #11

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3056. Min Act: -0.0000

Data Index: 798421 (The Pile)

Max Activating Token Index: 581

Text #12

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1742768 (The Pile)

Max Activating Token Index: 561

Text #13

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1649081 (The Pile)

Max Activating Token Index: 170

Text #14

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.2848. Min Act: -0.0000

Data Index: 817950 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.2832. Min Act: -0.0000

Data Index: 676597 (The Pile)

Max Activating Token Index: 468

Text #16

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.2948. Min Act: -0.0000

Data Index: 401111 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1052249 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1866067 (The Pile)

Max Activating Token Index: 353

Text #19

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.2780. Min Act: -0.0000

Data Index: 103602 (The Pile)

Max Activating Token Index: 280