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

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

Neuron 1149 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3193. Min Range: -3.3193

Max Act: 3.3193. Min Act: -0.0000

Data Index: 27544 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 3.3193. Min Range: -3.3193

Max Act: 3.2082. Min Act: -0.0000

Data Index: 1585743 (Python Code)

Max Activating Token Index: 174

Text #2

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.7257. Min Act: -0.0000

Data Index: 1229384 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 3.3193. Min Range: -3.3193

Max Act: 3.0985. Min Act: -0.0000

Data Index: 974710 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.8433. Min Act: -0.0000

Data Index: 1647985 (Python Code)

Max Activating Token Index: 658

Text #5

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.7881. Min Act: -0.0000

Data Index: 267392 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.7555. Min Act: -0.0000

Data Index: 1476999 (Python Code)

Max Activating Token Index: 77

Text #7

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.8463. Min Act: -0.0000

Data Index: 1604339 (Python Code)

Max Activating Token Index: 837

Text #8

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.7043. Min Act: -0.0000

Data Index: 570211 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.5547. Min Act: -0.0000

Data Index: 1544406 (Python Code)

Max Activating Token Index: 896

Text #10

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.6796. Min Act: -0.0000

Data Index: 1501299 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.6732. Min Act: -0.0000

Data Index: 1600888 (Python Code)

Max Activating Token Index: 473

Text #12

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.5376. Min Act: -0.0000

Data Index: 1395905 (Python Code)

Max Activating Token Index: 254

Text #13

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.5821. Min Act: -0.0000

Data Index: 1558521 (Python Code)

Max Activating Token Index: 109

Text #14

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.5540. Min Act: -0.0000

Data Index: 1409471 (Python Code)

Max Activating Token Index: 285

Text #15

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.7306. Min Act: -0.0000

Data Index: 316188 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.7037. Min Act: -0.0000

Data Index: 1621997 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.5711. Min Act: -0.0000

Data Index: 1571304 (Python Code)

Max Activating Token Index: 474

Text #18

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.5560. Min Act: -0.0000

Data Index: 1437937 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 3.3193. Min Range: -3.3193

Max Act: 2.5519. Min Act: -0.0000

Data Index: 1538405 (Python Code)

Max Activating Token Index: 524