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

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

Neuron 3640 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.3132. Min Act: -0.0001

Data Index: 913313 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2977. Min Act: -0.0001

Data Index: 910852 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2271. Min Act: -0.0001

Data Index: 109584 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2534. Min Act: -0.0001

Data Index: 420046 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2240. Min Act: -0.0001

Data Index: 104805 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2020. Min Act: -0.0001

Data Index: 406221 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1992. Min Act: -0.0001

Data Index: 193351 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2047. Min Act: -0.0001

Data Index: 107454 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1991. Min Act: -0.0001

Data Index: 782812 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1927. Min Act: -0.0001

Data Index: 194790 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1961. Min Act: -0.0001

Data Index: 143608 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1204970 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1918. Min Act: -0.0001

Data Index: 777870 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1979. Min Act: -0.0001

Data Index: 848513 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1274767 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1821. Min Act: -0.0001

Data Index: 1160827 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1745. Min Act: -0.0001

Data Index: 1271332 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1772. Min Act: -0.0001

Data Index: 85401 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1991. Min Act: -0.0001

Data Index: 1359562 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1157082 (C4 (Web Text))

Max Activating Token Index: 953