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

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

Neuron 656 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3650. Min Range: -4.3650

Max Act: 4.3650. Min Act: -0.0002

Data Index: 356252 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.8897. Min Act: -0.0002

Data Index: 1312128 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.7867. Min Act: -0.0002

Data Index: 927625 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.7345. Min Act: -0.0002

Data Index: 973894 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.5363. Min Act: -0.0002

Data Index: 864218 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.7598. Min Act: -0.0002

Data Index: 1079325 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.3230. Min Act: -0.0002

Data Index: 51323 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.4113. Min Act: -0.0002

Data Index: 919258 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.2725. Min Act: -0.0002

Data Index: 497570 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.2663. Min Act: -0.0002

Data Index: 1100266 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.2603. Min Act: -0.0002

Data Index: 789591 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.3531. Min Act: -0.0002

Data Index: 1001437 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.0604. Min Act: -0.0002

Data Index: 1173246 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.1863. Min Act: -0.0002

Data Index: 455395 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 4.3650. Min Range: -4.3650

Max Act: 2.7309. Min Act: -0.0002

Data Index: 392568 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.0018. Min Act: -0.0002

Data Index: 144135 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 4.3650. Min Range: -4.3650

Max Act: 2.9578. Min Act: -0.0002

Data Index: 285309 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 4.3650. Min Range: -4.3650

Max Act: 2.7805. Min Act: -0.0002

Data Index: 1255857 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.0998. Min Act: -0.0002

Data Index: 788900 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 4.3650. Min Range: -4.3650

Max Act: 2.9437. Min Act: -0.0002

Data Index: 480983 (C4 (Web Text))

Max Activating Token Index: 609