Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4425 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7321. Min Range: -4.7321

Max Act: 4.7321. Min Act: -0.0000

Data Index: 813582 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 4.7321. Min Range: -4.7321

Max Act: 4.2732. Min Act: -0.0000

Data Index: 334713 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.6889. Min Act: -0.0000

Data Index: 1269207 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.9848. Min Act: -0.0000

Data Index: 292665 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.9372. Min Act: -0.0000

Data Index: 1157781 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 4.7321. Min Range: -4.7321

Max Act: 4.1500. Min Act: -0.0000

Data Index: 1109425 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.9000. Min Act: -0.0000

Data Index: 1109390 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.8833. Min Act: -0.0000

Data Index: 434779 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.8739. Min Act: -0.0000

Data Index: 115319 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 4.7321. Min Range: -4.7321

Max Act: 4.0408. Min Act: -0.0000

Data Index: 684114 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.8746. Min Act: -0.0000

Data Index: 1263161 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.6421. Min Act: -0.0000

Data Index: 1188529 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.6008. Min Act: -0.0000

Data Index: 612735 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.8873. Min Act: -0.0000

Data Index: 134795 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.7066. Min Act: -0.0000

Data Index: 652826 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.8613. Min Act: -0.0000

Data Index: 1112668 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.6982. Min Act: -0.0000

Data Index: 877037 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.6680. Min Act: -0.0000

Data Index: 28077 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.6895. Min Act: -0.0000

Data Index: 1296538 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 4.7321. Min Range: -4.7321

Max Act: 3.8455. Min Act: -0.0000

Data Index: 305946 (C4 (Web Text))

Max Activating Token Index: 978