Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4020 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.2484. Min Range: -4.2484

Max Act: 4.2484. Min Act: -0.0000

Data Index: 528414 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 4.2484. Min Range: -4.2484

Max Act: 3.8365. Min Act: -0.0000

Data Index: 1027904 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 4.2484. Min Range: -4.2484

Max Act: 3.1778. Min Act: -0.0001

Data Index: 391465 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 4.2484. Min Range: -4.2484

Max Act: 3.1540. Min Act: -0.0000

Data Index: 1359652 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 4.2484. Min Range: -4.2484

Max Act: 3.1956. Min Act: -0.0000

Data Index: 1156742 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.8321. Min Act: -0.0000

Data Index: 550526 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 4.2484. Min Range: -4.2484

Max Act: 3.0139. Min Act: -0.0000

Data Index: 528871 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.6933. Min Act: -0.0001

Data Index: 78927 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.4108. Min Act: -0.0000

Data Index: 982614 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.5201. Min Act: -0.0000

Data Index: 839742 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.9087. Min Act: -0.0000

Data Index: 981146 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.4692. Min Act: -0.0000

Data Index: 1260666 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.4019. Min Act: -0.0000

Data Index: 959554 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.1281. Min Act: -0.0001

Data Index: 1177901 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.3647. Min Act: -0.0000

Data Index: 226695 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.2179. Min Act: -0.0000

Data Index: 86343 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.3361. Min Act: -0.0001

Data Index: 712024 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.3010. Min Act: -0.0001

Data Index: 942666 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.1529. Min Act: -0.0000

Data Index: 418485 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 4.2484. Min Range: -4.2484

Max Act: 2.2743. Min Act: -0.0000

Data Index: 213553 (C4 (Web Text))

Max Activating Token Index: 147