Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1670 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.7774. Min Act: -0.0001

Data Index: 1591463 (Python Code)

Max Activating Token Index: 171

Text #1

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.7075. Min Act: -0.0001

Data Index: 1434232 (Python Code)

Max Activating Token Index: 484

Text #2

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.7023. Min Act: -0.0001

Data Index: 1587227 (Python Code)

Max Activating Token Index: 928

Text #3

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.6452. Min Act: -0.0001

Data Index: 1519703 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.6507. Min Act: -0.0001

Data Index: 1493454 (Python Code)

Max Activating Token Index: 966

Text #5

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.6379. Min Act: -0.0001

Data Index: 1521551 (Python Code)

Max Activating Token Index: 87

Text #6

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5237. Min Act: -0.0001

Data Index: 1440446 (Python Code)

Max Activating Token Index: 287

Text #7

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5664. Min Act: -0.0001

Data Index: 1376589 (Python Code)

Max Activating Token Index: 284

Text #8

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.6279. Min Act: -0.0001

Data Index: 1645378 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5674. Min Act: -0.0001

Data Index: 1471323 (Python Code)

Max Activating Token Index: 315

Text #10

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.6006. Min Act: -0.0001

Data Index: 1498885 (Python Code)

Max Activating Token Index: 46

Text #11

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5812. Min Act: -0.0001

Data Index: 1497980 (Python Code)

Max Activating Token Index: 634

Text #12

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5485. Min Act: -0.0001

Data Index: 1387367 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.6138. Min Act: -0.0001

Data Index: 1376104 (Python Code)

Max Activating Token Index: 47

Text #14

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.6016. Min Act: -0.0001

Data Index: 1460119 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5904. Min Act: -0.0001

Data Index: 1612325 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5884. Min Act: -0.0001

Data Index: 1553925 (Python Code)

Max Activating Token Index: 228

Text #17

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5592. Min Act: -0.0001

Data Index: 1427284 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5824. Min Act: -0.0001

Data Index: 1513462 (Python Code)

Max Activating Token Index: 458

Text #19

Max Range: 0.7774. Min Range: -0.7774

Max Act: 0.5048. Min Act: -0.0001

Data Index: 1577378 (Python Code)

Max Activating Token Index: 266