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

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

Neuron 3524 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.4518. Min Act: -0.0000

Data Index: 1301676 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.4171. Min Act: -0.0000

Data Index: 904318 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.4902. Min Act: -0.0000

Data Index: 1267488 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.3839. Min Act: -0.0000

Data Index: 531679 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.3323. Min Act: -0.0000

Data Index: 493191 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.1996. Min Act: -0.0000

Data Index: 992680 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.0925. Min Act: -0.0000

Data Index: 518390 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1170876 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.1986. Min Act: -0.0000

Data Index: 876417 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1135388 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.2172. Min Act: -0.0000

Data Index: 516767 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.0321. Min Act: -0.0000

Data Index: 613742 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.1695. Min Act: -0.0000

Data Index: 1004385 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.0823. Min Act: -0.0000

Data Index: 1626122 (Python Code)

Max Activating Token Index: 234

Text #14

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.0231. Min Act: -0.0000

Data Index: 1651532 (Python Code)

Max Activating Token Index: 173

Text #15

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.0103. Min Act: -0.0000

Data Index: 575821 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.0019. Min Act: -0.0000

Data Index: 954206 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.0616. Min Act: -0.0000

Data Index: 505906 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1400059 (Python Code)

Max Activating Token Index: 596

Text #19

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1579512 (Python Code)

Max Activating Token Index: 771