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

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

Neuron 4065 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: 1.3002. Min Range: -1.3002

Max Act: 1.3002. Min Act: -0.0000

Data Index: 1625519 (Python Code)

Max Activating Token Index: 266

Text #1

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.2506. Min Act: -0.0000

Data Index: 297035 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1119169 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.1848. Min Act: -0.0000

Data Index: 1428810 (Python Code)

Max Activating Token Index: 465

Text #4

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.1869. Min Act: -0.0000

Data Index: 769654 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1001109 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0813. Min Act: -0.0000

Data Index: 1362746 (Python Code)

Max Activating Token Index: 869

Text #7

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0658. Min Act: -0.0000

Data Index: 360575 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1622798 (Python Code)

Max Activating Token Index: 524

Text #9

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1649267 (Python Code)

Max Activating Token Index: 98

Text #10

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.1429. Min Act: -0.0000

Data Index: 1550747 (Python Code)

Max Activating Token Index: 919

Text #11

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.1032. Min Act: -0.0000

Data Index: 765610 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1273569 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0750. Min Act: -0.0000

Data Index: 130325 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0668. Min Act: -0.0000

Data Index: 1629965 (Python Code)

Max Activating Token Index: 731

Text #15

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1078986 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0654. Min Act: -0.0000

Data Index: 1641171 (Python Code)

Max Activating Token Index: 331

Text #17

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0665. Min Act: -0.0000

Data Index: 1473050 (Python Code)

Max Activating Token Index: 766

Text #18

Max Range: 1.3002. Min Range: -1.3002

Max Act: 0.9740. Min Act: -0.0000

Data Index: 1480366 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 1.3002. Min Range: -1.3002

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1523179 (Python Code)

Max Activating Token Index: 671