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

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

Neuron 3199 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.3061. Min Act: -0.0002

Data Index: 773540 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2558. Min Act: -0.0002

Data Index: 730944 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.3203. Min Act: -0.0002

Data Index: 692393 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2577. Min Act: -0.0002

Data Index: 92355 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2988. Min Act: -0.0002

Data Index: 523050 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2468. Min Act: -0.0002

Data Index: 1338910 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2029. Min Act: -0.0002

Data Index: 804705 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1741. Min Act: -0.0002

Data Index: 859387 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1184. Min Act: -0.0002

Data Index: 461655 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2779. Min Act: -0.0002

Data Index: 967412 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2518. Min Act: -0.0002

Data Index: 956815 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2043. Min Act: -0.0002

Data Index: 1207534 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2137. Min Act: -0.0002

Data Index: 496546 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1440. Min Act: -0.0002

Data Index: 145866 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1805. Min Act: -0.0002

Data Index: 1085142 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2144. Min Act: -0.0002

Data Index: 1169729 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1048. Min Act: -0.0002

Data Index: 303368 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1327. Min Act: -0.0002

Data Index: 1176398 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1678. Min Act: -0.0002

Data Index: 1325355 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1365. Min Act: -0.0002

Data Index: 906827 (C4 (Web Text))

Max Activating Token Index: 93