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

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

Neuron 1307 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2326. Min Range: -3.2326

Max Act: 3.1926. Min Act: -0.0000

Data Index: 1387480 (Python Code)

Max Activating Token Index: 370

Text #1

Max Range: 3.2326. Min Range: -3.2326

Max Act: 3.2326. Min Act: -0.0000

Data Index: 711893 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.9658. Min Act: -0.0000

Data Index: 208877 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.7413. Min Act: -0.0000

Data Index: 1573950 (Python Code)

Max Activating Token Index: 445

Text #4

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.4898. Min Act: -0.0000

Data Index: 54642 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.6954. Min Act: -0.0000

Data Index: 1406449 (Python Code)

Max Activating Token Index: 537

Text #6

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.2404. Min Act: -0.0000

Data Index: 1528858 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.2918. Min Act: -0.0000

Data Index: 94095 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 3.2326. Min Range: -3.2326

Max Act: 1.9936. Min Act: -0.0000

Data Index: 1186170 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.2401. Min Act: -0.0000

Data Index: 654771 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.0952. Min Act: -0.0000

Data Index: 1608834 (Python Code)

Max Activating Token Index: 639

Text #11

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.2642. Min Act: -0.0000

Data Index: 1621337 (Python Code)

Max Activating Token Index: 764

Text #12

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.1148. Min Act: -0.0000

Data Index: 1233548 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 3.2326. Min Range: -3.2326

Max Act: 1.8432. Min Act: -0.0000

Data Index: 1339627 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.0701. Min Act: -0.0000

Data Index: 230145 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.0599. Min Act: -0.0000

Data Index: 1104183 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 3.2326. Min Range: -3.2326

Max Act: 1.9046. Min Act: -0.0000

Data Index: 208446 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.0403. Min Act: -0.0000

Data Index: 799802 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 3.2326. Min Range: -3.2326

Max Act: 1.6795. Min Act: -0.0000

Data Index: 796906 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 3.2326. Min Range: -3.2326

Max Act: 2.0619. Min Act: -0.0000

Data Index: 1487259 (Python Code)

Max Activating Token Index: 693