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

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

Neuron 5897 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.2843. Min Act: -0.0001

Data Index: 616254 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.2613. Min Act: -0.0000

Data Index: 750247 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.1326. Min Act: -0.0001

Data Index: 1071903 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.1518. Min Act: -0.0000

Data Index: 780422 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.1502. Min Act: -0.0001

Data Index: 708976 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.0837. Min Act: -0.0001

Data Index: 1060488 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.1262. Min Act: -0.0001

Data Index: 1153967 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.0404. Min Act: -0.0001

Data Index: 341672 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.0874. Min Act: -0.0000

Data Index: 708931 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.0615. Min Act: -0.0001

Data Index: 386429 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.0610. Min Act: -0.0000

Data Index: 434590 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.0283. Min Act: -0.0001

Data Index: 225039 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 1.2843. Min Range: -1.2843

Max Act: 1.0830. Min Act: -0.0000

Data Index: 415811 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 1.2843. Min Range: -1.2843

Max Act: 0.9893. Min Act: -0.0001

Data Index: 1293628 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 1.2843. Min Range: -1.2843

Max Act: 0.9827. Min Act: -0.0001

Data Index: 1325641 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 1.2843. Min Range: -1.2843

Max Act: 0.9579. Min Act: -0.0001

Data Index: 1177600 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 1.2843. Min Range: -1.2843

Max Act: 0.9545. Min Act: -0.0000

Data Index: 281761 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 1.2843. Min Range: -1.2843

Max Act: 0.9687. Min Act: -0.0001

Data Index: 1195190 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 1.2843. Min Range: -1.2843

Max Act: 0.9623. Min Act: -0.0001

Data Index: 1258474 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 1.2843. Min Range: -1.2843

Max Act: 0.9234. Min Act: -0.0000

Data Index: 1177125 (C4 (Web Text))

Max Activating Token Index: 182