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

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

Neuron 966 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1202620 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1595355 (Python Code)

Max Activating Token Index: 226

Text #2

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1424909 (Python Code)

Max Activating Token Index: 549

Text #3

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1505276 (Python Code)

Max Activating Token Index: 532

Text #4

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1200760 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4562. Min Act: -0.0000

Data Index: 59575 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4431. Min Act: -0.0000

Data Index: 171224 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1430265 (Python Code)

Max Activating Token Index: 438

Text #8

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4270. Min Act: -0.0000

Data Index: 361945 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1298521 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1252307 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1541202 (Python Code)

Max Activating Token Index: 765

Text #12

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1044297 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1367715 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1420670 (Python Code)

Max Activating Token Index: 277

Text #15

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3900. Min Act: -0.0000

Data Index: 749679 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3956. Min Act: -0.0000

Data Index: 27084 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4065. Min Act: -0.0000

Data Index: 402918 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1620724 (Python Code)

Max Activating Token Index: 549

Text #19

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1556009 (Python Code)

Max Activating Token Index: 916