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

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

Neuron 3517 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1512. Min Range: -1.1512

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1258459 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.6408. Min Act: -0.0000

Data Index: 424813 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1512396 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1430499 (Python Code)

Max Activating Token Index: 142

Text #4

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1050722 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.4348. Min Act: -0.0000

Data Index: 934977 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.4417. Min Act: -0.0000

Data Index: 998813 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.4227. Min Act: -0.0000

Data Index: 103949 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1587929 (Python Code)

Max Activating Token Index: 446

Text #9

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1380284 (Python Code)

Max Activating Token Index: 352

Text #10

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.4224. Min Act: -0.0000

Data Index: 925897 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.4205. Min Act: -0.0000

Data Index: 58329 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.4030. Min Act: -0.0000

Data Index: 15210 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1540519 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1442102 (Python Code)

Max Activating Token Index: 364

Text #15

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.3907. Min Act: -0.0000

Data Index: 1448053 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1644977 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1362895 (Python Code)

Max Activating Token Index: 676

Text #18

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.3487. Min Act: -0.0000

Data Index: 316130 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1574865 (Python Code)

Max Activating Token Index: 578