Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1110 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2804. Min Range: -1.2804

Max Act: 1.2804. Min Act: -0.0001

Data Index: 445474 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 1.2804. Min Range: -1.2804

Max Act: 1.0531. Min Act: -0.0000

Data Index: 755026 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.9709. Min Act: -0.0001

Data Index: 400367 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.8322. Min Act: -0.0001

Data Index: 883852 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.8018. Min Act: -0.0001

Data Index: 871544 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.7580. Min Act: -0.0001

Data Index: 341488 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.7263. Min Act: -0.0001

Data Index: 586936 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.7280. Min Act: -0.0001

Data Index: 1083729 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.7289. Min Act: -0.0001

Data Index: 659682 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.7433. Min Act: -0.0001

Data Index: 633013 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.6974. Min Act: -0.0001

Data Index: 1028272 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.7473. Min Act: -0.0001

Data Index: 1292543 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.6932. Min Act: -0.0001

Data Index: 447180 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.6410. Min Act: -0.0001

Data Index: 15109 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.6875. Min Act: -0.0001

Data Index: 84099 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.7030. Min Act: -0.0001

Data Index: 1074346 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.6616. Min Act: -0.0001

Data Index: 25112 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.6593. Min Act: -0.0001

Data Index: 350093 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.6823. Min Act: -0.0001

Data Index: 1012705 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.6941. Min Act: -0.0001

Data Index: 431594 (C4 (Web Text))

Max Activating Token Index: 918