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

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

Neuron 5074 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: 0.9392. Min Range: -0.9392

Max Act: 0.9392. Min Act: -0.0000

Data Index: 296313 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.8164. Min Act: -0.0000

Data Index: 634643 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.8187. Min Act: -0.0000

Data Index: 756146 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6824. Min Act: -0.0000

Data Index: 42380 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1649274 (Python Code)

Max Activating Token Index: 602

Text #5

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.7043. Min Act: -0.0000

Data Index: 1394880 (Python Code)

Max Activating Token Index: 797

Text #6

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.8016. Min Act: -0.0000

Data Index: 1329369 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1393121 (Python Code)

Max Activating Token Index: 898

Text #8

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6658. Min Act: -0.0000

Data Index: 516917 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.7228. Min Act: -0.0000

Data Index: 975392 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6771. Min Act: -0.0000

Data Index: 814600 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1115160 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1521646 (Python Code)

Max Activating Token Index: 112

Text #13

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1566543 (Python Code)

Max Activating Token Index: 759

Text #14

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1638133 (Python Code)

Max Activating Token Index: 229

Text #15

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1108740 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1457786 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1437396 (Python Code)

Max Activating Token Index: 854

Text #18

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5995. Min Act: -0.0000

Data Index: 464039 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1379176 (Python Code)

Max Activating Token Index: 522