Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 792 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.8602. Min Act: -0.0001

Data Index: 74061 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.9502. Min Act: -0.0001

Data Index: 915699 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.8661. Min Act: -0.0001

Data Index: 1225804 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.7610. Min Act: -0.0001

Data Index: 1117960 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.7940. Min Act: -0.0001

Data Index: 159601 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.7940. Min Act: -0.0001

Data Index: 707975 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.7940. Min Act: -0.0001

Data Index: 1124431 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.7940. Min Act: -0.0001

Data Index: 1134152 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.7940. Min Act: -0.0001

Data Index: 792950 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.7967. Min Act: -0.0001

Data Index: 444357 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6707. Min Act: -0.0001

Data Index: 204910 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6903. Min Act: -0.0001

Data Index: 1282282 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.7432. Min Act: -0.0001

Data Index: 171533 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6477. Min Act: -0.0001

Data Index: 1167223 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6341. Min Act: -0.0001

Data Index: 1090380 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6102. Min Act: -0.0001

Data Index: 197473 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6460. Min Act: -0.0001

Data Index: 1218208 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6094. Min Act: -0.0001

Data Index: 124245 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5298. Min Act: -0.0001

Data Index: 1114156 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5147. Min Act: -0.0001

Data Index: 92355 (C4 (Web Text))

Max Activating Token Index: 538