Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1522 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0826. Min Range: -3.0826

Max Act: 3.0826. Min Act: -0.0000

Data Index: 960183 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8617. Min Act: -0.0000

Data Index: 456452 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.9055. Min Act: -0.0000

Data Index: 1034308 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8355. Min Act: -0.0000

Data Index: 869860 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.4822. Min Act: -0.0000

Data Index: 947308 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.5713. Min Act: -0.0000

Data Index: 398933 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.5337. Min Act: -0.0000

Data Index: 1229247 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.5557. Min Act: -0.0000

Data Index: 296827 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.5371. Min Act: -0.0000

Data Index: 358089 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.3903. Min Act: -0.0000

Data Index: 1065974 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.4900. Min Act: -0.0000

Data Index: 530607 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.4705. Min Act: -0.0000

Data Index: 682612 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.4619. Min Act: -0.0000

Data Index: 896082 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.5672. Min Act: -0.0000

Data Index: 181803 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.2448. Min Act: -0.0000

Data Index: 538385 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.3641. Min Act: -0.0000

Data Index: 1192466 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.3492. Min Act: -0.0000

Data Index: 270451 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.1729. Min Act: -0.0000

Data Index: 250313 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.2977. Min Act: -0.0000

Data Index: 622358 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.1646. Min Act: -0.0000

Data Index: 571420 (C4 (Web Text))

Max Activating Token Index: 978