Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1360 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.3237. Min Act: -0.0001

Data Index: 754467 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2796. Min Act: -0.0001

Data Index: 484000 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2175. Min Act: -0.0001

Data Index: 889964 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2098. Min Act: -0.0001

Data Index: 114124 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1966. Min Act: -0.0001

Data Index: 1281565 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1686. Min Act: -0.0001

Data Index: 7739 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1258. Min Act: -0.0001

Data Index: 736817 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1720. Min Act: -0.0001

Data Index: 520409 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1593. Min Act: -0.0001

Data Index: 781196 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1322692 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1685. Min Act: -0.0001

Data Index: 632171 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1617. Min Act: -0.0001

Data Index: 410832 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1616. Min Act: -0.0001

Data Index: 459429 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1644. Min Act: -0.0001

Data Index: 514462 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1233873 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1587. Min Act: -0.0001

Data Index: 154391 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1746. Min Act: -0.0001

Data Index: 1071648 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1556. Min Act: -0.0001

Data Index: 215651 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1262727 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.1489. Min Act: -0.0001

Data Index: 578906 (C4 (Web Text))

Max Activating Token Index: 95