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

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

Neuron 5068 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: 0.6431. Min Range: -0.6431

Max Act: 0.6431. Min Act: -0.0000

Data Index: 968516 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1504321 (Python Code)

Max Activating Token Index: 462

Text #2

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1490416 (Python Code)

Max Activating Token Index: 439

Text #3

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1507668 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1403660 (Python Code)

Max Activating Token Index: 707

Text #5

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1631885 (Python Code)

Max Activating Token Index: 75

Text #6

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1451021 (Python Code)

Max Activating Token Index: 891

Text #7

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1361556 (Python Code)

Max Activating Token Index: 135

Text #8

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1596427 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1524395 (Python Code)

Max Activating Token Index: 224

Text #10

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1645443 (Python Code)

Max Activating Token Index: 319

Text #11

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1588479 (Python Code)

Max Activating Token Index: 434

Text #12

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1565813 (Python Code)

Max Activating Token Index: 252

Text #13

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4399. Min Act: -0.0000

Data Index: 1616719 (Python Code)

Max Activating Token Index: 365

Text #14

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1444133 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1530507 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1636530 (Python Code)

Max Activating Token Index: 715

Text #17

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1653794 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1482647 (Python Code)

Max Activating Token Index: 356

Text #19

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1619235 (Python Code)

Max Activating Token Index: 175