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

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

Neuron 2241 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4802. Min Range: -2.4802

Max Act: 2.4802. Min Act: -0.0000

Data Index: 348055 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 2.4802. Min Range: -2.4802

Max Act: 2.2853. Min Act: -0.0000

Data Index: 1082302 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 2.4802. Min Range: -2.4802

Max Act: 2.2457. Min Act: -0.0000

Data Index: 564260 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 2.4802. Min Range: -2.4802

Max Act: 2.1665. Min Act: -0.0000

Data Index: 107117 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 2.4802. Min Range: -2.4802

Max Act: 2.0493. Min Act: -0.0000

Data Index: 75288 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 2.4802. Min Range: -2.4802

Max Act: 2.0505. Min Act: -0.0000

Data Index: 1273724 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 2.4802. Min Range: -2.4802

Max Act: 2.0414. Min Act: -0.0000

Data Index: 1052839 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 2.4802. Min Range: -2.4802

Max Act: 1.9488. Min Act: -0.0000

Data Index: 481124 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 2.4802. Min Range: -2.4802

Max Act: 1.8980. Min Act: -0.0000

Data Index: 148555 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 2.4802. Min Range: -2.4802

Max Act: 1.8990. Min Act: -0.0000

Data Index: 887979 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 2.4802. Min Range: -2.4802

Max Act: 1.9822. Min Act: -0.0000

Data Index: 1134135 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 2.4802. Min Range: -2.4802

Max Act: 2.0731. Min Act: -0.0000

Data Index: 1040033 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 2.4802. Min Range: -2.4802

Max Act: 1.9576. Min Act: -0.0000

Data Index: 1284721 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 2.4802. Min Range: -2.4802

Max Act: 2.0731. Min Act: -0.0000

Data Index: 399640 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 2.4802. Min Range: -2.4802

Max Act: 1.9681. Min Act: -0.0000

Data Index: 1353249 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 2.4802. Min Range: -2.4802

Max Act: 1.8414. Min Act: -0.0000

Data Index: 1186264 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 2.4802. Min Range: -2.4802

Max Act: 1.9506. Min Act: -0.0000

Data Index: 651184 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 2.4802. Min Range: -2.4802

Max Act: 1.9247. Min Act: -0.0000

Data Index: 612323 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 2.4802. Min Range: -2.4802

Max Act: 1.9944. Min Act: -0.0000

Data Index: 48494 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 2.4802. Min Range: -2.4802

Max Act: 1.9751. Min Act: -0.0000

Data Index: 941455 (C4 (Web Text))

Max Activating Token Index: 76