Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3713 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.7852. Min Act: -0.0000

Data Index: 1480835 (Python Code)

Max Activating Token Index: 448

Text #1

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.5499. Min Act: -0.0001

Data Index: 1455386 (Python Code)

Max Activating Token Index: 186

Text #2

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.3143. Min Act: -0.0000

Data Index: 1435412 (Python Code)

Max Activating Token Index: 242

Text #3

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.3231. Min Act: -0.0000

Data Index: 1596704 (Python Code)

Max Activating Token Index: 172

Text #4

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.2194. Min Act: -0.0000

Data Index: 1625869 (Python Code)

Max Activating Token Index: 31

Text #5

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.4313. Min Act: -0.0001

Data Index: 1550232 (Python Code)

Max Activating Token Index: 210

Text #6

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.3327. Min Act: -0.0000

Data Index: 1597807 (Python Code)

Max Activating Token Index: 492

Text #7

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.3117. Min Act: -0.0000

Data Index: 1578928 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.2965. Min Act: -0.0000

Data Index: 1443415 (Python Code)

Max Activating Token Index: 340

Text #9

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.2979. Min Act: -0.0000

Data Index: 1401085 (Python Code)

Max Activating Token Index: 81

Text #10

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.2960. Min Act: -0.0001

Data Index: 1542474 (Python Code)

Max Activating Token Index: 265

Text #11

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.1511. Min Act: -0.0000

Data Index: 1391375 (Python Code)

Max Activating Token Index: 535

Text #12

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.1734. Min Act: -0.0000

Data Index: 1617735 (Python Code)

Max Activating Token Index: 424

Text #13

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.0908. Min Act: -0.0001

Data Index: 1523811 (Python Code)

Max Activating Token Index: 620

Text #14

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.3357. Min Act: -0.0000

Data Index: 1583105 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.3228. Min Act: -0.0000

Data Index: 1487490 (Python Code)

Max Activating Token Index: 463

Text #16

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.3096. Min Act: -0.0000

Data Index: 1466788 (Python Code)

Max Activating Token Index: 521

Text #17

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.0781. Min Act: -0.0001

Data Index: 1625439 (Python Code)

Max Activating Token Index: 239

Text #18

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.2966. Min Act: -0.0001

Data Index: 1451141 (Python Code)

Max Activating Token Index: 533

Text #19

Max Range: 2.7852. Min Range: -2.7852

Max Act: 2.1177. Min Act: -0.0000

Data Index: 1433914 (Python Code)

Max Activating Token Index: 41