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

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

Neuron 5410 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.7728. Min Act: -0.0000

Data Index: 1652042 (Python Code)

Max Activating Token Index: 671

Text #1

Max Range: 3.0507. Min Range: -3.0507

Max Act: 3.0507. Min Act: -0.0000

Data Index: 1491680 (Python Code)

Max Activating Token Index: 184

Text #2

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.9091. Min Act: -0.0000

Data Index: 1495753 (Python Code)

Max Activating Token Index: 424

Text #3

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.8922. Min Act: -0.0000

Data Index: 1532791 (Python Code)

Max Activating Token Index: 631

Text #4

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.7445. Min Act: -0.0000

Data Index: 1652269 (Python Code)

Max Activating Token Index: 598

Text #5

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.5992. Min Act: -0.0000

Data Index: 1639809 (Python Code)

Max Activating Token Index: 947

Text #6

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.8756. Min Act: -0.0000

Data Index: 1542251 (Python Code)

Max Activating Token Index: 859

Text #7

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.8188. Min Act: -0.0000

Data Index: 1487100 (Python Code)

Max Activating Token Index: 528

Text #8

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.7606. Min Act: -0.0000

Data Index: 1576668 (Python Code)

Max Activating Token Index: 813

Text #9

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.7604. Min Act: -0.0000

Data Index: 1615580 (Python Code)

Max Activating Token Index: 400

Text #10

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.7516. Min Act: -0.0000

Data Index: 1655104 (Python Code)

Max Activating Token Index: 706

Text #11

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.6071. Min Act: -0.0000

Data Index: 1479908 (Python Code)

Max Activating Token Index: 546

Text #12

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.7392. Min Act: -0.0000

Data Index: 1390823 (Python Code)

Max Activating Token Index: 579

Text #13

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.6081. Min Act: -0.0000

Data Index: 1470765 (Python Code)

Max Activating Token Index: 515

Text #14

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.7168. Min Act: -0.0000

Data Index: 1363074 (Python Code)

Max Activating Token Index: 524

Text #15

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.7001. Min Act: -0.0000

Data Index: 1418344 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.5486. Min Act: -0.0000

Data Index: 1600881 (Python Code)

Max Activating Token Index: 762

Text #17

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.5217. Min Act: -0.0000

Data Index: 1506861 (Python Code)

Max Activating Token Index: 289

Text #18

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.5404. Min Act: -0.0000

Data Index: 1591508 (Python Code)

Max Activating Token Index: 348

Text #19

Max Range: 3.0507. Min Range: -3.0507

Max Act: 2.7960. Min Act: -0.0000

Data Index: 1424897 (Python Code)

Max Activating Token Index: 789