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

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

Neuron 3794 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: 3.7585. Min Range: -3.7585

Max Act: 3.7585. Min Act: -0.0000

Data Index: 1432221 (Python Code)

Max Activating Token Index: 736

Text #1

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.6942. Min Act: -0.0000

Data Index: 1503902 (Python Code)

Max Activating Token Index: 772

Text #2

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.2297. Min Act: -0.0000

Data Index: 1393305 (Python Code)

Max Activating Token Index: 713

Text #3

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.3322. Min Act: -0.0000

Data Index: 1453866 (Python Code)

Max Activating Token Index: 678

Text #4

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.1609. Min Act: -0.0000

Data Index: 1462537 (Python Code)

Max Activating Token Index: 183

Text #5

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.3020. Min Act: -0.0000

Data Index: 1440723 (Python Code)

Max Activating Token Index: 628

Text #6

Max Range: 3.7585. Min Range: -3.7585

Max Act: 2.9659. Min Act: -0.0000

Data Index: 1486187 (Python Code)

Max Activating Token Index: 383

Text #7

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.2219. Min Act: -0.0000

Data Index: 1538900 (Python Code)

Max Activating Token Index: 529

Text #8

Max Range: 3.7585. Min Range: -3.7585

Max Act: 2.9286. Min Act: -0.0000

Data Index: 1541767 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.0590. Min Act: -0.0000

Data Index: 1394229 (Python Code)

Max Activating Token Index: 391

Text #10

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.0580. Min Act: -0.0000

Data Index: 1630331 (Python Code)

Max Activating Token Index: 393

Text #11

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.0588. Min Act: -0.0000

Data Index: 1580141 (Python Code)

Max Activating Token Index: 965

Text #12

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.0113. Min Act: -0.0000

Data Index: 1638933 (Python Code)

Max Activating Token Index: 858

Text #13

Max Range: 3.7585. Min Range: -3.7585

Max Act: 2.7298. Min Act: -0.0000

Data Index: 1400833 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.0244. Min Act: -0.0000

Data Index: 1504515 (Python Code)

Max Activating Token Index: 298

Text #15

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.0111. Min Act: -0.0000

Data Index: 1379495 (Python Code)

Max Activating Token Index: 215

Text #16

Max Range: 3.7585. Min Range: -3.7585

Max Act: 2.7459. Min Act: -0.0000

Data Index: 1386665 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.0078. Min Act: -0.0000

Data Index: 1644758 (Python Code)

Max Activating Token Index: 184

Text #18

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.1574. Min Act: -0.0000

Data Index: 1508166 (Python Code)

Max Activating Token Index: 151

Text #19

Max Range: 3.7585. Min Range: -3.7585

Max Act: 3.0002. Min Act: -0.0000

Data Index: 1481438 (Python Code)

Max Activating Token Index: 169