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

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

Neuron 4209 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1349. Min Range: -1.1349

Max Act: 1.1349. Min Act: -0.0000

Data Index: 992415 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 1.1349. Min Range: -1.1349

Max Act: 1.1080. Min Act: -0.0000

Data Index: 784640 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 1.1349. Min Range: -1.1349

Max Act: 1.0457. Min Act: -0.0000

Data Index: 695722 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 1.1349. Min Range: -1.1349

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1021136 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.9574. Min Act: -0.0000

Data Index: 506129 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.8836. Min Act: -0.0000

Data Index: 757461 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.8668. Min Act: 0.0000

Data Index: 579501 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.7928. Min Act: -0.0000

Data Index: 466049 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.7871. Min Act: -0.0000

Data Index: 646205 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.7630. Min Act: -0.0000

Data Index: 299624 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.7570. Min Act: -0.0000

Data Index: 364018 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.7520. Min Act: -0.0000

Data Index: 181168 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.7649. Min Act: -0.0000

Data Index: 975705 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1081931 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.7404. Min Act: 0.0000

Data Index: 813128 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.6627. Min Act: -0.0000

Data Index: 692651 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.6893. Min Act: -0.0000

Data Index: 669695 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.7020. Min Act: 0.0000

Data Index: 647887 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.6178. Min Act: -0.0000

Data Index: 891413 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 1.1349. Min Range: -1.1349

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1270394 (C4 (Web Text))

Max Activating Token Index: 393