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

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

Neuron 4605 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.0049. Min Act: -0.0000

Data Index: 523948 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 4.1234. Min Range: -4.1234

Max Act: 3.8304. Min Act: -0.0000

Data Index: 1255849 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 4.1234. Min Range: -4.1234

Max Act: 4.1234. Min Act: -0.0000

Data Index: 52385 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 4.1234. Min Range: -4.1234

Max Act: 3.6806. Min Act: -0.0000

Data Index: 238721 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 4.1234. Min Range: -4.1234

Max Act: 2.9988. Min Act: -0.0000

Data Index: 1165179 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 4.1234. Min Range: -4.1234

Max Act: 2.8637. Min Act: -0.0000

Data Index: 1282525 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 4.1234. Min Range: -4.1234

Max Act: 2.6475. Min Act: -0.0000

Data Index: 1253922 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 4.1234. Min Range: -4.1234

Max Act: 2.3784. Min Act: -0.0000

Data Index: 511269 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 4.1234. Min Range: -4.1234

Max Act: 2.2982. Min Act: -0.0000

Data Index: 330725 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 4.1234. Min Range: -4.1234

Max Act: 2.1606. Min Act: -0.0000

Data Index: 339026 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 4.1234. Min Range: -4.1234

Max Act: 2.3004. Min Act: -0.0000

Data Index: 3096 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 4.1234. Min Range: -4.1234

Max Act: 2.1306. Min Act: -0.0000

Data Index: 1310444 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 4.1234. Min Range: -4.1234

Max Act: 1.9256. Min Act: -0.0000

Data Index: 845115 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 4.1234. Min Range: -4.1234

Max Act: 1.9996. Min Act: -0.0000

Data Index: 83835 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 4.1234. Min Range: -4.1234

Max Act: 1.8983. Min Act: -0.0000

Data Index: 1036631 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 4.1234. Min Range: -4.1234

Max Act: 1.4277. Min Act: -0.0000

Data Index: 861489 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 4.1234. Min Range: -4.1234

Max Act: 1.8703. Min Act: -0.0000

Data Index: 816545 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 4.1234. Min Range: -4.1234

Max Act: 1.6135. Min Act: -0.0000

Data Index: 258820 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 4.1234. Min Range: -4.1234

Max Act: 1.5130. Min Act: -0.0000

Data Index: 662764 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 4.1234. Min Range: -4.1234

Max Act: 1.5901. Min Act: -0.0000

Data Index: 312831 (C4 (Web Text))

Max Activating Token Index: 950