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

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

Neuron 692 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: 0.2298. Min Range: -0.2298

Max Act: 0.2298. Min Act: -0.0001

Data Index: 949619 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.2168. Min Act: -0.0001

Data Index: 1194443 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1983. Min Act: -0.0001

Data Index: 35572 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1924. Min Act: -0.0001

Data Index: 867856 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.2042. Min Act: -0.0001

Data Index: 189958 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1882. Min Act: -0.0001

Data Index: 144172 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1973. Min Act: -0.0001

Data Index: 508680 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.2021. Min Act: -0.0001

Data Index: 16863 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1910. Min Act: -0.0001

Data Index: 387294 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1907. Min Act: -0.0001

Data Index: 971019 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1967. Min Act: -0.0001

Data Index: 1197163 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1854. Min Act: -0.0001

Data Index: 264325 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.2031. Min Act: -0.0001

Data Index: 683985 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1619. Min Act: -0.0001

Data Index: 222738 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1814. Min Act: -0.0001

Data Index: 331815 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1609. Min Act: -0.0001

Data Index: 35671 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1692. Min Act: -0.0001

Data Index: 1308206 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1756. Min Act: -0.0001

Data Index: 707591 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1335261 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1474. Min Act: -0.0001

Data Index: 562319 (C4 (Web Text))

Max Activating Token Index: 482