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

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

Neuron 2219 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9444. Min Range: -5.9444

Max Act: 5.9444. Min Act: -0.0000

Data Index: 1366100 (Python Code)

Max Activating Token Index: 790

Text #1

Max Range: 5.9444. Min Range: -5.9444

Max Act: 5.3038. Min Act: -0.0000

Data Index: 1625792 (Python Code)

Max Activating Token Index: 41

Text #2

Max Range: 5.9444. Min Range: -5.9444

Max Act: 5.0131. Min Act: -0.0000

Data Index: 1431652 (Python Code)

Max Activating Token Index: 736

Text #3

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.8855. Min Act: -0.0000

Data Index: 1507840 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.8453. Min Act: -0.0000

Data Index: 1651119 (Python Code)

Max Activating Token Index: 112

Text #5

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.4338. Min Act: -0.0000

Data Index: 1507242 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.5834. Min Act: -0.0000

Data Index: 1385512 (Python Code)

Max Activating Token Index: 826

Text #7

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.5258. Min Act: -0.0000

Data Index: 1370503 (Python Code)

Max Activating Token Index: 190

Text #8

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.8952. Min Act: -0.0000

Data Index: 1642080 (Python Code)

Max Activating Token Index: 406

Text #9

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.6725. Min Act: -0.0000

Data Index: 1444637 (Python Code)

Max Activating Token Index: 549

Text #10

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.4844. Min Act: -0.0000

Data Index: 1368071 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.6368. Min Act: -0.0000

Data Index: 1621086 (Python Code)

Max Activating Token Index: 485

Text #12

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.4176. Min Act: -0.0000

Data Index: 1377794 (Python Code)

Max Activating Token Index: 492

Text #13

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.4193. Min Act: -0.0000

Data Index: 1592575 (Python Code)

Max Activating Token Index: 478

Text #14

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.3853. Min Act: -0.0000

Data Index: 1549479 (Python Code)

Max Activating Token Index: 768

Text #15

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.4990. Min Act: -0.0000

Data Index: 1392814 (Python Code)

Max Activating Token Index: 885

Text #16

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.1476. Min Act: -0.0000

Data Index: 1552615 (Python Code)

Max Activating Token Index: 742

Text #17

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.0380. Min Act: -0.0000

Data Index: 1493603 (Python Code)

Max Activating Token Index: 762

Text #18

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.0360. Min Act: -0.0000

Data Index: 1561962 (Python Code)

Max Activating Token Index: 313

Text #19

Max Range: 5.9444. Min Range: -5.9444

Max Act: 4.0168. Min Act: -0.0000

Data Index: 1420888 (Python Code)

Max Activating Token Index: 765