Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 641 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0005

Data Index: 1409383 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0220. Min Act: -0.0005

Data Index: 1644297 (Python Code)

Max Activating Token Index: 855

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0202. Min Act: -0.0005

Data Index: 1485044 (Python Code)

Max Activating Token Index: 728

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0167. Min Act: -0.0005

Data Index: 949273 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0164. Min Act: -0.0005

Data Index: 1384925 (Python Code)

Max Activating Token Index: 593

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0162. Min Act: -0.0005

Data Index: 1647392 (Python Code)

Max Activating Token Index: 794

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0154. Min Act: -0.0005

Data Index: 1557724 (Python Code)

Max Activating Token Index: 534

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0164. Min Act: -0.0004

Data Index: 596766 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0160. Min Act: -0.0004

Data Index: 477977 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0160. Min Act: -0.0005

Data Index: 1484149 (Python Code)

Max Activating Token Index: 591

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0163. Min Act: -0.0005

Data Index: 500346 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0155. Min Act: -0.0005

Data Index: 1552663 (Python Code)

Max Activating Token Index: 508

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0162. Min Act: -0.0005

Data Index: 1455922 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0155. Min Act: -0.0005

Data Index: 1630024 (Python Code)

Max Activating Token Index: 363

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0158. Min Act: -0.0005

Data Index: 1610802 (Python Code)

Max Activating Token Index: 569

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0157. Min Act: -0.0005

Data Index: 1464019 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0156. Min Act: -0.0005

Data Index: 1450201 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0155. Min Act: -0.0005

Data Index: 1203724 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0155. Min Act: -0.0005

Data Index: 1491743 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0154. Min Act: -0.0005

Data Index: 1603728 (Python Code)

Max Activating Token Index: 882