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

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

Neuron 2013 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8970. Min Range: -3.8970

Max Act: 3.6384. Min Act: -0.0000

Data Index: 913221 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 3.8970. Min Range: -3.8970

Max Act: 3.7573. Min Act: -0.0000

Data Index: 798342 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 3.8970. Min Range: -3.8970

Max Act: 3.7199. Min Act: -0.0000

Data Index: 575698 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 3.8970. Min Range: -3.8970

Max Act: 3.8970. Min Act: -0.0000

Data Index: 1149435 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 3.8970. Min Range: -3.8970

Max Act: 3.6864. Min Act: -0.0000

Data Index: 1281834 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 3.8970. Min Range: -3.8970

Max Act: 3.5088. Min Act: -0.0000

Data Index: 255030 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 3.8970. Min Range: -3.8970

Max Act: 3.5112. Min Act: -0.0000

Data Index: 1156974 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 3.8970. Min Range: -3.8970

Max Act: 3.7055. Min Act: -0.0000

Data Index: 105011 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 3.8970. Min Range: -3.8970

Max Act: 3.5385. Min Act: -0.0000

Data Index: 8232 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 3.8970. Min Range: -3.8970

Max Act: 3.5201. Min Act: -0.0000

Data Index: 1058899 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 3.8970. Min Range: -3.8970

Max Act: 3.5529. Min Act: -0.0000

Data Index: 548390 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 3.8970. Min Range: -3.8970

Max Act: 2.9876. Min Act: -0.0000

Data Index: 968794 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 3.8970. Min Range: -3.8970

Max Act: 3.0533. Min Act: -0.0000

Data Index: 1336596 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 3.8970. Min Range: -3.8970

Max Act: 2.9389. Min Act: -0.0000

Data Index: 42041 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 3.8970. Min Range: -3.8970

Max Act: 2.9237. Min Act: -0.0000

Data Index: 555401 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 3.8970. Min Range: -3.8970

Max Act: 2.8130. Min Act: -0.0000

Data Index: 801380 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 3.8970. Min Range: -3.8970

Max Act: 2.9553. Min Act: -0.0000

Data Index: 646795 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 3.8970. Min Range: -3.8970

Max Act: 2.9362. Min Act: -0.0000

Data Index: 1225492 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 3.8970. Min Range: -3.8970

Max Act: 2.8032. Min Act: -0.0000

Data Index: 25853 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 3.8970. Min Range: -3.8970

Max Act: 2.9319. Min Act: -0.0000

Data Index: 233933 (C4 (Web Text))

Max Activating Token Index: 102