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

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

Neuron 3651 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.1425. Min Act: -0.0001

Data Index: 1578870 (Python Code)

Max Activating Token Index: 92

Text #1

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9973. Min Act: -0.0001

Data Index: 1585036 (Python Code)

Max Activating Token Index: 666

Text #2

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.0941. Min Act: -0.0001

Data Index: 1370602 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9925. Min Act: -0.0001

Data Index: 1639719 (Python Code)

Max Activating Token Index: 939

Text #4

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.0466. Min Act: -0.0001

Data Index: 1489395 (Python Code)

Max Activating Token Index: 84

Text #5

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.1037. Min Act: -0.0001

Data Index: 1609288 (Python Code)

Max Activating Token Index: 217

Text #6

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.0627. Min Act: -0.0001

Data Index: 1365470 (Python Code)

Max Activating Token Index: 455

Text #7

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9888. Min Act: -0.0001

Data Index: 1456731 (Python Code)

Max Activating Token Index: 553

Text #8

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.1505. Min Act: -0.0001

Data Index: 1386879 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.0204. Min Act: -0.0001

Data Index: 1442908 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9896. Min Act: -0.0001

Data Index: 1551304 (Python Code)

Max Activating Token Index: 109

Text #11

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9345. Min Act: -0.0001

Data Index: 1373241 (Python Code)

Max Activating Token Index: 936

Text #12

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.0722. Min Act: -0.0001

Data Index: 1463023 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.0269. Min Act: -0.0001

Data Index: 1361976 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9140. Min Act: -0.0001

Data Index: 1493837 (Python Code)

Max Activating Token Index: 255

Text #15

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.1507. Min Act: -0.0001

Data Index: 1532484 (Python Code)

Max Activating Token Index: 224

Text #16

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9872. Min Act: -0.0001

Data Index: 1629092 (Python Code)

Max Activating Token Index: 197

Text #17

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9020. Min Act: -0.0001

Data Index: 1480214 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9861. Min Act: -0.0001

Data Index: 1459952 (Python Code)

Max Activating Token Index: 208

Text #19

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9829. Min Act: -0.0001

Data Index: 1613656 (Python Code)

Max Activating Token Index: 96