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

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

Neuron 3067 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: 3.0667. Min Range: -3.0667

Max Act: 3.0170. Min Act: -0.0000

Data Index: 1615044 (Python Code)

Max Activating Token Index: 132

Text #1

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.8920. Min Act: -0.0000

Data Index: 1615176 (Python Code)

Max Activating Token Index: 284

Text #2

Max Range: 3.0667. Min Range: -3.0667

Max Act: 3.0667. Min Act: -0.0000

Data Index: 1490486 (Python Code)

Max Activating Token Index: 948

Text #3

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.7405. Min Act: -0.0000

Data Index: 1386259 (Python Code)

Max Activating Token Index: 734

Text #4

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.7569. Min Act: -0.0000

Data Index: 1489239 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.7466. Min Act: -0.0000

Data Index: 1486136 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 3.0667. Min Range: -3.0667

Max Act: 3.0007. Min Act: -0.0000

Data Index: 1552107 (Python Code)

Max Activating Token Index: 314

Text #7

Max Range: 3.0667. Min Range: -3.0667

Max Act: 3.0139. Min Act: -0.0000

Data Index: 1523964 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.7161. Min Act: -0.0000

Data Index: 1488287 (Python Code)

Max Activating Token Index: 191

Text #9

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.6317. Min Act: -0.0000

Data Index: 1639286 (Python Code)

Max Activating Token Index: 693

Text #10

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.6168. Min Act: -0.0000

Data Index: 1611579 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.4652. Min Act: -0.0000

Data Index: 1527163 (Python Code)

Max Activating Token Index: 934

Text #12

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.4615. Min Act: -0.0000

Data Index: 1384518 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.4154. Min Act: -0.0000

Data Index: 1458411 (Python Code)

Max Activating Token Index: 812

Text #14

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.3775. Min Act: -0.0000

Data Index: 1636672 (Python Code)

Max Activating Token Index: 285

Text #15

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.3305. Min Act: -0.0000

Data Index: 1564856 (Python Code)

Max Activating Token Index: 820

Text #16

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.3038. Min Act: -0.0000

Data Index: 1430556 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.2160. Min Act: -0.0000

Data Index: 1565354 (Python Code)

Max Activating Token Index: 980

Text #18

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.2196. Min Act: -0.0000

Data Index: 1484303 (Python Code)

Max Activating Token Index: 266

Text #19

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.1770. Min Act: -0.0000

Data Index: 1600430 (Python Code)

Max Activating Token Index: 456