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

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

Neuron 1781 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0604. Min Range: -1.0604

Max Act: 1.0604. Min Act: -0.0000

Data Index: 449627 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 1.0604. Min Range: -1.0604

Max Act: 1.0601. Min Act: -0.0000

Data Index: 928084 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1126333 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.8230. Min Act: -0.0000

Data Index: 1107021 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1008387 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.8901. Min Act: -0.0000

Data Index: 1351774 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.8596. Min Act: -0.0000

Data Index: 771796 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7905. Min Act: -0.0000

Data Index: 915665 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1222065 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7980. Min Act: -0.0000

Data Index: 747795 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1113763 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7315. Min Act: -0.0000

Data Index: 386273 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7566. Min Act: -0.0000

Data Index: 612431 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7779. Min Act: -0.0000

Data Index: 967935 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1301103 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.6965. Min Act: -0.0000

Data Index: 910366 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.6730. Min Act: -0.0000

Data Index: 522932 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1010421 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.6834. Min Act: -0.0000

Data Index: 860979 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.6520. Min Act: -0.0000

Data Index: 918115 (C4 (Web Text))

Max Activating Token Index: 728