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

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

Neuron 4481 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.7353. Min Act: -0.0001

Data Index: 870151 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.5081. Min Act: -0.0000

Data Index: 377026 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.5747. Min Act: -0.0000

Data Index: 834717 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.5023. Min Act: -0.0001

Data Index: 563467 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.3984. Min Act: -0.0001

Data Index: 516169 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.4543. Min Act: -0.0001

Data Index: 201697 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.3227. Min Act: -0.0001

Data Index: 336334 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.3550. Min Act: -0.0001

Data Index: 992758 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.3462. Min Act: -0.0001

Data Index: 221731 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.3995. Min Act: -0.0001

Data Index: 887795 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.3558. Min Act: -0.0000

Data Index: 686772 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.2855. Min Act: -0.0001

Data Index: 785409 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.1585. Min Act: -0.0000

Data Index: 353866 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.2845. Min Act: -0.0001

Data Index: 679038 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.3163. Min Act: -0.0001

Data Index: 880340 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.2015. Min Act: -0.0001

Data Index: 1310622 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.1274. Min Act: -0.0000

Data Index: 999670 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.1588. Min Act: -0.0001

Data Index: 39346 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.2903. Min Act: -0.0001

Data Index: 321468 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 1.7353. Min Range: -1.7353

Max Act: 1.1086. Min Act: -0.0001

Data Index: 580039 (C4 (Web Text))

Max Activating Token Index: 523