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

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

Neuron 1441 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.4120. Min Act: -0.0001

Data Index: 24531 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.4300. Min Act: -0.0001

Data Index: 551375 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3953. Min Act: -0.0001

Data Index: 626120 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.4237. Min Act: -0.0001

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.4137. Min Act: -0.0001

Data Index: 895702 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.4159. Min Act: -0.0001

Data Index: 1181731 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.4096. Min Act: -0.0001

Data Index: 1216439 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3432. Min Act: -0.0001

Data Index: 412185 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3876. Min Act: -0.0001

Data Index: 615826 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3954. Min Act: -0.0001

Data Index: 1143545 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.4007. Min Act: -0.0001

Data Index: 219677 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3639. Min Act: -0.0001

Data Index: 336224 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3854. Min Act: -0.0001

Data Index: 729032 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3502. Min Act: -0.0001

Data Index: 1017414 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3586. Min Act: -0.0001

Data Index: 1251201 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3647. Min Act: -0.0001

Data Index: 534531 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3379. Min Act: -0.0001

Data Index: 886674 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3347. Min Act: -0.0001

Data Index: 59476 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3715. Min Act: -0.0001

Data Index: 792918 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.4300. Min Range: -0.4300

Max Act: 0.3865. Min Act: -0.0001

Data Index: 1344917 (C4 (Web Text))

Max Activating Token Index: 452