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

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

Neuron 3164 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: 1.4796. Min Range: -1.4796

Max Act: 1.4796. Min Act: -0.0000

Data Index: 553452 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.4624. Min Act: -0.0000

Data Index: 127660 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.2802. Min Act: -0.0000

Data Index: 797687 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.2221. Min Act: -0.0000

Data Index: 777524 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1175262 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.1620. Min Act: -0.0000

Data Index: 598402 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1151854 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.1535. Min Act: -0.0000

Data Index: 1120532 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1089086 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.2128. Min Act: -0.0000

Data Index: 163133 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.1551. Min Act: -0.0000

Data Index: 603573 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0895. Min Act: -0.0000

Data Index: 578609 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0850. Min Act: -0.0000

Data Index: 340584 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0608. Min Act: -0.0000

Data Index: 560560 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0932. Min Act: -0.0000

Data Index: 93653 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0526. Min Act: -0.0000

Data Index: 689720 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.1024. Min Act: -0.0000

Data Index: 473521 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0250. Min Act: -0.0000

Data Index: 575574 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1228304 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0812. Min Act: -0.0000

Data Index: 356876 (C4 (Web Text))

Max Activating Token Index: 844