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

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

Neuron 4800 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.3066. Min Act: -0.0000

Data Index: 972136 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.1999. Min Act: -0.0000

Data Index: 1466309 (Python Code)

Max Activating Token Index: 736

Text #2

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1384176 (Python Code)

Max Activating Token Index: 610

Text #3

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0165. Min Act: -0.0000

Data Index: 1372832 (Python Code)

Max Activating Token Index: 847

Text #4

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1442873 (Python Code)

Max Activating Token Index: 866

Text #5

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1594022 (Python Code)

Max Activating Token Index: 500

Text #6

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1652457 (Python Code)

Max Activating Token Index: 677

Text #7

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1004890 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.9148. Min Act: -0.0000

Data Index: 663545 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.8317. Min Act: -0.0000

Data Index: 199685 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.7412. Min Act: -0.0000

Data Index: 47279 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1454782 (Python Code)

Max Activating Token Index: 874

Text #12

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.8022. Min Act: -0.0000

Data Index: 695838 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.7737. Min Act: -0.0000

Data Index: 1467527 (Python Code)

Max Activating Token Index: 201

Text #14

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1529745 (Python Code)

Max Activating Token Index: 853

Text #15

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.7218. Min Act: -0.0000

Data Index: 1606501 (Python Code)

Max Activating Token Index: 802

Text #16

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.7530. Min Act: -0.0000

Data Index: 662767 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.7537. Min Act: -0.0000

Data Index: 144873 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.7564. Min Act: -0.0000

Data Index: 291113 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.7125. Min Act: -0.0000

Data Index: 379643 (C4 (Web Text))

Max Activating Token Index: 802