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

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

Neuron 4975 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.4778. Min Act: -0.0000

Data Index: 375989 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.4568. Min Act: -0.0000

Data Index: 1277050 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.3249. Min Act: -0.0000

Data Index: 148853 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.2905. Min Act: -0.0000

Data Index: 122399 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.2232. Min Act: -0.0000

Data Index: 591746 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.0877. Min Act: -0.0000

Data Index: 946353 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.1367. Min Act: -0.0000

Data Index: 349242 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.1138. Min Act: -0.0000

Data Index: 997095 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.1107. Min Act: -0.0000

Data Index: 921096 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.0948. Min Act: -0.0000

Data Index: 118669 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.1047. Min Act: -0.0000

Data Index: 1204120 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.0853. Min Act: -0.0000

Data Index: 608166 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.0965. Min Act: -0.0000

Data Index: 398437 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.0162. Min Act: -0.0000

Data Index: 1125129 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.0892. Min Act: -0.0000

Data Index: 1112555 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.0747. Min Act: -0.0000

Data Index: 363611 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.0676. Min Act: -0.0000

Data Index: 735179 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.0210. Min Act: -0.0000

Data Index: 721332 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 1.4778. Min Range: -1.4778

Max Act: 1.0505. Min Act: -0.0000

Data Index: 1328720 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.4778. Min Range: -1.4778

Max Act: 0.9754. Min Act: -0.0000

Data Index: 918649 (C4 (Web Text))

Max Activating Token Index: 591