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

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

Neuron 3488 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.9267. Min Act: -0.0000

Data Index: 536639 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1488186 (Python Code)

Max Activating Token Index: 401

Text #2

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8303. Min Act: -0.0000

Data Index: 697558 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1653132 (Python Code)

Max Activating Token Index: 454

Text #4

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1654805 (Python Code)

Max Activating Token Index: 786

Text #5

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1519489 (Python Code)

Max Activating Token Index: 437

Text #6

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1556460 (Python Code)

Max Activating Token Index: 767

Text #7

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1489246 (Python Code)

Max Activating Token Index: 358

Text #8

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1364129 (Python Code)

Max Activating Token Index: 605

Text #9

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1597350 (Python Code)

Max Activating Token Index: 684

Text #10

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1427634 (Python Code)

Max Activating Token Index: 515

Text #11

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1162275 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1499996 (Python Code)

Max Activating Token Index: 762

Text #13

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1537268 (Python Code)

Max Activating Token Index: 984

Text #14

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1541315 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6749. Min Act: -0.0000

Data Index: 1654478 (Python Code)

Max Activating Token Index: 969

Text #16

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1384317 (Python Code)

Max Activating Token Index: 778

Text #17

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6825. Min Act: -0.0000

Data Index: 1654144 (Python Code)

Max Activating Token Index: 690

Text #18

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1618669 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6154. Min Act: -0.0000

Data Index: 707914 (C4 (Web Text))

Max Activating Token Index: 629