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

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

Neuron 473 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1632622 (Python Code)

Max Activating Token Index: 731

Text #1

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1525467 (Python Code)

Max Activating Token Index: 214

Text #2

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1607327 (Python Code)

Max Activating Token Index: 39

Text #3

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1460878 (Python Code)

Max Activating Token Index: 238

Text #4

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1565346 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1485964 (Python Code)

Max Activating Token Index: 681

Text #6

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.7107. Min Act: -0.0000

Data Index: 1614317 (Python Code)

Max Activating Token Index: 614

Text #7

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1369683 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1502154 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1582103 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1388479 (Python Code)

Max Activating Token Index: 560

Text #11

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1635183 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1383746 (Python Code)

Max Activating Token Index: 786

Text #13

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1468602 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1625192 (Python Code)

Max Activating Token Index: 417

Text #15

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1440508 (Python Code)

Max Activating Token Index: 340

Text #16

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1487600 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1409605 (Python Code)

Max Activating Token Index: 462

Text #18

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1525161 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 0.8472. Min Range: -0.8472

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1410047 (Python Code)

Max Activating Token Index: 108