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

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

Neuron 3884 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: 0.3168. Min Range: -0.3168

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1232649 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1151554 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2255. Min Act: -0.0000

Data Index: 810389 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1191784 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1615431 (Python Code)

Max Activating Token Index: 297

Text #5

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1457075 (Python Code)

Max Activating Token Index: 471

Text #6

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2091. Min Act: -0.0000

Data Index: 909028 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1392547 (Python Code)

Max Activating Token Index: 340

Text #8

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1834. Min Act: -0.0000

Data Index: 756278 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1406063 (Python Code)

Max Activating Token Index: 423

Text #10

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1801. Min Act: -0.0000

Data Index: 1369258 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1013808 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1643413 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1451480 (Python Code)

Max Activating Token Index: 945

Text #14

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1271233 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1790. Min Act: -0.0001

Data Index: 1298627 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1568033 (Python Code)

Max Activating Token Index: 549

Text #17

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1496. Min Act: -0.0001

Data Index: 1517517 (Python Code)

Max Activating Token Index: 846

Text #18

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1649. Min Act: -0.0001

Data Index: 1502216 (Python Code)

Max Activating Token Index: 78

Text #19

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1482911 (Python Code)

Max Activating Token Index: 473