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

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

Neuron 2630 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.8659. Min Act: -0.0002

Data Index: 686154 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.8182. Min Act: -0.0003

Data Index: 1286619 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.8114. Min Act: -0.0002

Data Index: 719166 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7880. Min Act: -0.0001

Data Index: 1481162 (Python Code)

Max Activating Token Index: 290

Text #4

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7888. Min Act: -0.0002

Data Index: 530405 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7836. Min Act: -0.0002

Data Index: 1581021 (Python Code)

Max Activating Token Index: 312

Text #6

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7879. Min Act: -0.0002

Data Index: 817763 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7878. Min Act: -0.0002

Data Index: 1555949 (Python Code)

Max Activating Token Index: 338

Text #8

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7724. Min Act: -0.0002

Data Index: 1477573 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7686. Min Act: -0.0002

Data Index: 1569326 (Python Code)

Max Activating Token Index: 350

Text #10

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7716. Min Act: -0.0002

Data Index: 1607012 (Python Code)

Max Activating Token Index: 214

Text #11

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7816. Min Act: -0.0001

Data Index: 1396242 (Python Code)

Max Activating Token Index: 344

Text #12

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7664. Min Act: -0.0002

Data Index: 1638737 (Python Code)

Max Activating Token Index: 672

Text #13

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7567. Min Act: -0.0003

Data Index: 1301419 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7640. Min Act: -0.0002

Data Index: 1640980 (Python Code)

Max Activating Token Index: 710

Text #15

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7607. Min Act: -0.0002

Data Index: 1532186 (Python Code)

Max Activating Token Index: 740

Text #16

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7688. Min Act: -0.0002

Data Index: 1509322 (Python Code)

Max Activating Token Index: 290

Text #17

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7574. Min Act: -0.0002

Data Index: 1484880 (Python Code)

Max Activating Token Index: 1019

Text #18

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7658. Min Act: -0.0002

Data Index: 1608774 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7682. Min Act: -0.0002

Data Index: 1411208 (Python Code)

Max Activating Token Index: 967