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

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

Neuron 2125 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.6876. Min Act: -0.0000

Data Index: 65456 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4922. Min Act: -0.0000

Data Index: 246351 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5109. Min Act: -0.0000

Data Index: 399018 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4926. Min Act: -0.0000

Data Index: 433174 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1043302 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5042. Min Act: -0.0000

Data Index: 745481 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4805. Min Act: -0.0000

Data Index: 891333 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1485794 (Python Code)

Max Activating Token Index: 188

Text #8

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4609. Min Act: -0.0000

Data Index: 292612 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4771. Min Act: -0.0000

Data Index: 278470 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4272. Min Act: -0.0000

Data Index: 502299 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4678. Min Act: -0.0000

Data Index: 351738 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1551080 (Python Code)

Max Activating Token Index: 538

Text #13

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4126. Min Act: -0.0000

Data Index: 682138 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1607252 (Python Code)

Max Activating Token Index: 863

Text #15

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.3834. Min Act: -0.0000

Data Index: 99432 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4064. Min Act: -0.0000

Data Index: 389890 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1337894 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.3981. Min Act: -0.0000

Data Index: 506736 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.3646. Min Act: -0.0000

Data Index: 485736 (C4 (Web Text))

Max Activating Token Index: 296