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

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

Neuron 3077 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1612975 (Python Code)

Max Activating Token Index: 309

Text #1

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1450913 (Python Code)

Max Activating Token Index: 92

Text #2

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1457689 (Python Code)

Max Activating Token Index: 809

Text #3

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1447403 (Python Code)

Max Activating Token Index: 203

Text #4

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1417114 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1517259 (Python Code)

Max Activating Token Index: 469

Text #6

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1579180 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1422244 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1633684 (Python Code)

Max Activating Token Index: 528

Text #9

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1569555 (Python Code)

Max Activating Token Index: 299

Text #10

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6886. Min Act: 0.0000

Data Index: 1553363 (Python Code)

Max Activating Token Index: 588

Text #11

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1648121 (Python Code)

Max Activating Token Index: 671

Text #12

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1498755 (Python Code)

Max Activating Token Index: 311

Text #13

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1650366 (Python Code)

Max Activating Token Index: 496

Text #14

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6511. Min Act: 0.0000

Data Index: 1645327 (Python Code)

Max Activating Token Index: 327

Text #15

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6455. Min Act: 0.0000

Data Index: 1589117 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1594687 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1384097 (Python Code)

Max Activating Token Index: 138

Text #18

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1403517 (Python Code)

Max Activating Token Index: 718

Text #19

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1496653 (Python Code)

Max Activating Token Index: 874