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

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

Neuron 14 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.3860. Min Range: -8.3860

Max Act: 8.3860. Min Act: -0.0000

Data Index: 1064017 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 8.3860. Min Range: -8.3860

Max Act: 8.2392. Min Act: -0.0000

Data Index: 145750 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.5350. Min Act: -0.0001

Data Index: 46856 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.2818. Min Act: -0.0001

Data Index: 927547 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.9100. Min Act: -0.0001

Data Index: 1106646 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.7233. Min Act: -0.0001

Data Index: 640901 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.5576. Min Act: -0.0001

Data Index: 1274529 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 8.3860. Min Range: -8.3860

Max Act: 8.3618. Min Act: -0.0001

Data Index: 650714 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 8.3860. Min Range: -8.3860

Max Act: 8.1994. Min Act: -0.0001

Data Index: 874406 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.6553. Min Act: -0.0001

Data Index: 760833 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.6310. Min Act: -0.0001

Data Index: 699356 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.6136. Min Act: -0.0001

Data Index: 1356839 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.5871. Min Act: -0.0001

Data Index: 132409 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.8968. Min Act: -0.0001

Data Index: 586610 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.7369. Min Act: -0.0001

Data Index: 660247 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.8845. Min Act: -0.0001

Data Index: 956544 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.3258. Min Act: -0.0001

Data Index: 165046 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.6695. Min Act: -0.0000

Data Index: 265131 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.6516. Min Act: -0.0000

Data Index: 1207520 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 8.3860. Min Range: -8.3860

Max Act: 7.6016. Min Act: -0.0000

Data Index: 1290242 (C4 (Web Text))

Max Activating Token Index: 1019