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

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

Neuron 639 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0643. Min Range: -4.0643

Max Act: 4.0643. Min Act: -0.0000

Data Index: 793804 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.7017. Min Act: -0.0000

Data Index: 207542 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.6828. Min Act: -0.0000

Data Index: 1044440 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.4370. Min Act: -0.0000

Data Index: 380499 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.0460. Min Act: -0.0000

Data Index: 1035246 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.8233. Min Act: -0.0000

Data Index: 143347 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.7865. Min Act: -0.0000

Data Index: 933223 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.8622. Min Act: -0.0000

Data Index: 427214 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.6160. Min Act: -0.0000

Data Index: 491043 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.8359. Min Act: -0.0000

Data Index: 65423 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.7840. Min Act: -0.0000

Data Index: 1010980 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.6519. Min Act: -0.0000

Data Index: 1300781 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.7286. Min Act: -0.0000

Data Index: 692837 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.4550. Min Act: -0.0000

Data Index: 94003 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.4416. Min Act: -0.0000

Data Index: 761885 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.1482. Min Act: -0.0000

Data Index: 513880 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.6292. Min Act: -0.0000

Data Index: 154314 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.3561. Min Act: -0.0000

Data Index: 1337426 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.1065. Min Act: -0.0000

Data Index: 1260 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 4.0643. Min Range: -4.0643

Max Act: 2.4515. Min Act: -0.0000

Data Index: 1200938 (C4 (Web Text))

Max Activating Token Index: 502