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

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

Neuron 5064 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: 0.9671. Min Range: -0.9671

Max Act: 0.9671. Min Act: -0.0000

Data Index: 447257 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1178085 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.8902. Min Act: -0.0000

Data Index: 1481133 (Python Code)

Max Activating Token Index: 631

Text #3

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.8450. Min Act: -0.0000

Data Index: 202387 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1098504 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.7880. Min Act: -0.0000

Data Index: 949763 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1203510 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1361034 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1171449 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1419423 (Python Code)

Max Activating Token Index: 823

Text #10

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6661. Min Act: -0.0000

Data Index: 547342 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6918. Min Act: -0.0000

Data Index: 232198 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1184439 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1292227 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6863. Min Act: -0.0000

Data Index: 639865 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1411719 (Python Code)

Max Activating Token Index: 439

Text #16

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6562. Min Act: -0.0000

Data Index: 153406 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6490. Min Act: -0.0000

Data Index: 248164 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1653230 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 0.9671. Min Range: -0.9671

Max Act: 0.6223. Min Act: -0.0000

Data Index: 635771 (C4 (Web Text))

Max Activating Token Index: 85