Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 767 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0477. Min Range: -1.0477

Max Act: 1.0477. Min Act: -0.0001

Data Index: 222193 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.9380. Min Act: -0.0001

Data Index: 196819 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.8569. Min Act: -0.0001

Data Index: 1270196 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.8229. Min Act: -0.0001

Data Index: 17914 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.8530. Min Act: -0.0001

Data Index: 154167 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.8120. Min Act: -0.0001

Data Index: 69643 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.8426. Min Act: -0.0001

Data Index: 316786 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7227. Min Act: -0.0001

Data Index: 893856 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7744. Min Act: -0.0001

Data Index: 1128402 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7916. Min Act: -0.0001

Data Index: 868927 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7906. Min Act: -0.0001

Data Index: 1287173 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7985. Min Act: -0.0001

Data Index: 229597 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7577. Min Act: -0.0001

Data Index: 959397 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7575. Min Act: -0.0001

Data Index: 675619 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7812. Min Act: -0.0001

Data Index: 1060815 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7099. Min Act: -0.0001

Data Index: 406726 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7708. Min Act: -0.0001

Data Index: 495955 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7380. Min Act: -0.0001

Data Index: 567650 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7460. Min Act: -0.0001

Data Index: 807624 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.6815. Min Act: -0.0001

Data Index: 476982 (C4 (Web Text))

Max Activating Token Index: 690