Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5173 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.7288. Min Act: -0.0001

Data Index: 151544 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.7352. Min Act: -0.0001

Data Index: 735804 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.7323. Min Act: -0.0001

Data Index: 697868 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6392. Min Act: -0.0001

Data Index: 27088 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.5732. Min Act: -0.0001

Data Index: 812362 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6603. Min Act: -0.0001

Data Index: 846670 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6103. Min Act: -0.0001

Data Index: 1123680 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.5397. Min Act: -0.0001

Data Index: 694628 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.5862. Min Act: -0.0001

Data Index: 792307 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6758. Min Act: -0.0001

Data Index: 1083473 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.5722. Min Act: -0.0001

Data Index: 637897 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6128. Min Act: -0.0001

Data Index: 669822 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6000. Min Act: -0.0001

Data Index: 75419 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.5014. Min Act: -0.0001

Data Index: 581702 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.4964. Min Act: -0.0001

Data Index: 1126899 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1221388 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.4859. Min Act: -0.0001

Data Index: 508621 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.5202. Min Act: -0.0001

Data Index: 1028881 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.5135. Min Act: -0.0001

Data Index: 389310 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.5183. Min Act: -0.0001

Data Index: 1298030 (C4 (Web Text))

Max Activating Token Index: 950