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

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

Neuron 4286 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4203. Min Range: -2.4203

Max Act: 2.4203. Min Act: -0.0000

Data Index: 1482703 (Python Code)

Max Activating Token Index: 410

Text #1

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.4687. Min Act: -0.0000

Data Index: 1369610 (Python Code)

Max Activating Token Index: 676

Text #2

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.4295. Min Act: -0.0000

Data Index: 1473815 (Python Code)

Max Activating Token Index: 476

Text #3

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.4310. Min Act: -0.0000

Data Index: 1639634 (Python Code)

Max Activating Token Index: 987

Text #4

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.4672. Min Act: -0.0000

Data Index: 1428363 (Python Code)

Max Activating Token Index: 564

Text #5

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.1975. Min Act: -0.0000

Data Index: 1360531 (Python Code)

Max Activating Token Index: 664

Text #6

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1438459 (Python Code)

Max Activating Token Index: 492

Text #7

Max Range: 2.4203. Min Range: -2.4203

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1502488 (Python Code)

Max Activating Token Index: 365

Text #8

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.1952. Min Act: -0.0000

Data Index: 484118 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1475832 (Python Code)

Max Activating Token Index: 305

Text #10

Max Range: 2.4203. Min Range: -2.4203

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1360622 (Python Code)

Max Activating Token Index: 1004

Text #11

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.1724. Min Act: -0.0000

Data Index: 1516580 (Python Code)

Max Activating Token Index: 505

Text #12

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.1137. Min Act: -0.0000

Data Index: 1509147 (Python Code)

Max Activating Token Index: 1018

Text #13

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.2299. Min Act: -0.0000

Data Index: 1596719 (Python Code)

Max Activating Token Index: 965

Text #14

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.0673. Min Act: -0.0000

Data Index: 983515 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.1673. Min Act: -0.0000

Data Index: 649501 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.0291. Min Act: -0.0000

Data Index: 1462007 (Python Code)

Max Activating Token Index: 437

Text #17

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.0811. Min Act: -0.0000

Data Index: 821695 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1377063 (Python Code)

Max Activating Token Index: 410

Text #19

Max Range: 2.4203. Min Range: -2.4203

Max Act: 1.0831. Min Act: -0.0000

Data Index: 513975 (C4 (Web Text))

Max Activating Token Index: 267