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

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

Neuron 4795 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.5876. Min Act: -0.0000

Data Index: 550306 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.8139. Min Act: -0.0000

Data Index: 743302 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.3721. Min Act: -0.0000

Data Index: 1250550 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.3749. Min Act: -0.0000

Data Index: 966262 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.3480. Min Act: -0.0000

Data Index: 1201709 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.2523. Min Act: -0.0000

Data Index: 551632 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.3590. Min Act: -0.0000

Data Index: 589387 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.3488. Min Act: -0.0000

Data Index: 879248 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.1911. Min Act: -0.0000

Data Index: 894827 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.2509. Min Act: -0.0000

Data Index: 1220241 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.2862. Min Act: -0.0000

Data Index: 1015406 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.1656. Min Act: -0.0000

Data Index: 527946 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.1028. Min Act: -0.0000

Data Index: 283889 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.1762. Min Act: -0.0000

Data Index: 1331919 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.1611. Min Act: -0.0000

Data Index: 345280 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.1663. Min Act: -0.0000

Data Index: 535191 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1078147 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.1849. Min Act: -0.0000

Data Index: 937829 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.0800. Min Act: -0.0000

Data Index: 221118 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.1004. Min Act: -0.0000

Data Index: 236440 (C4 (Web Text))

Max Activating Token Index: 433