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

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

Neuron 6042 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0898. Min Act: -0.0000

Data Index: 484096 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0950. Min Act: -0.0000

Data Index: 514125 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1478286 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0897. Min Act: -0.0000

Data Index: 812742 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1402597 (Python Code)

Max Activating Token Index: 673

Text #5

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1490682 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1124646 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0825. Min Act: -0.0000

Data Index: 705418 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1003223 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0845. Min Act: -0.0000

Data Index: 37076 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0808. Min Act: -0.0000

Data Index: 233374 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0770. Min Act: -0.0000

Data Index: 495860 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1541025 (Python Code)

Max Activating Token Index: 873

Text #13

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1493865 (Python Code)

Max Activating Token Index: 469

Text #14

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0783. Min Act: -0.0000

Data Index: 1362968 (Python Code)

Max Activating Token Index: 309

Text #15

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1195098 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0740. Min Act: -0.0000

Data Index: 431569 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1042455 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1465985 (Python Code)

Max Activating Token Index: 294

Text #19

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0809. Min Act: -0.0000

Data Index: 345255 (C4 (Web Text))

Max Activating Token Index: 714