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

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

Neuron 3614 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: 1.3314. Min Range: -1.3314

Max Act: 1.2775. Min Act: -0.0000

Data Index: 1239492 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 1.3314. Min Range: -1.3314

Max Act: 1.3314. Min Act: -0.0000

Data Index: 334535 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 1.3314. Min Range: -1.3314

Max Act: 1.1667. Min Act: -0.0000

Data Index: 819524 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.9902. Min Act: -0.0000

Data Index: 609386 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1291718 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 1.3314. Min Range: -1.3314

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1057139 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1480712 (Python Code)

Max Activating Token Index: 184

Text #7

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1032628 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.9557. Min Act: -0.0000

Data Index: 523905 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.9276. Min Act: -0.0000

Data Index: 907114 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.8536. Min Act: -0.0000

Data Index: 886502 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.8232. Min Act: -0.0000

Data Index: 493471 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1202511 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1489795 (Python Code)

Max Activating Token Index: 931

Text #14

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.8431. Min Act: -0.0000

Data Index: 980845 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1630344 (Python Code)

Max Activating Token Index: 374

Text #16

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.6643. Min Act: -0.0000

Data Index: 753242 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1206929 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1533020 (Python Code)

Max Activating Token Index: 852

Text #19

Max Range: 1.3314. Min Range: -1.3314

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1615151 (Python Code)

Max Activating Token Index: 542