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

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

Neuron 5905 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.5748. Min Act: -0.0000

Data Index: 902157 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.4852. Min Act: -0.0000

Data Index: 284896 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.4194. Min Act: -0.0000

Data Index: 243385 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.3932. Min Act: -0.0000

Data Index: 1168289 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.3781. Min Act: -0.0000

Data Index: 243277 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1013364 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.3426. Min Act: -0.0000

Data Index: 746363 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.3056. Min Act: -0.0000

Data Index: 1120750 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.2980. Min Act: -0.0000

Data Index: 1307653 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.2872. Min Act: -0.0000

Data Index: 320897 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.3521. Min Act: -0.0000

Data Index: 687027 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.2674. Min Act: -0.0000

Data Index: 54608 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1034646 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.2560. Min Act: -0.0000

Data Index: 712142 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.2485. Min Act: -0.0000

Data Index: 376413 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1307445 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.1387. Min Act: -0.0000

Data Index: 663223 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.2238. Min Act: -0.0000

Data Index: 943098 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.1482. Min Act: -0.0000

Data Index: 41972 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 1.5748. Min Range: -1.5748

Max Act: 1.0948. Min Act: -0.0000

Data Index: 991483 (C4 (Web Text))

Max Activating Token Index: 204