Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 883 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0313. Min Range: -1.0313

Max Act: 1.0313. Min Act: -0.0000

Data Index: 747959 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.9544. Min Act: -0.0000

Data Index: 625875 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6778. Min Act: -0.0000

Data Index: 815665 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.7101. Min Act: -0.0000

Data Index: 768881 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6442. Min Act: -0.0000

Data Index: 400436 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1356071 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6460. Min Act: -0.0000

Data Index: 939521 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6465. Min Act: -0.0000

Data Index: 348228 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6317. Min Act: -0.0000

Data Index: 831938 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1006803 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1376708 (Python Code)

Max Activating Token Index: 419

Text #11

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1653987 (Python Code)

Max Activating Token Index: 651

Text #12

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6218. Min Act: 0.0001

Data Index: 694350 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1419426 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6013. Min Act: -0.0000

Data Index: 464071 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.5441. Min Act: -0.0000

Data Index: 3436 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6059. Min Act: 0.0000

Data Index: 1429780 (Python Code)

Max Activating Token Index: 850

Text #17

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1512565 (Python Code)

Max Activating Token Index: 334

Text #18

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.6078. Min Act: 0.0000

Data Index: 1654956 (Python Code)

Max Activating Token Index: 910

Text #19

Max Range: 1.0313. Min Range: -1.0313

Max Act: 0.5929. Min Act: -0.0000

Data Index: 325169 (C4 (Web Text))

Max Activating Token Index: 353