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

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

Neuron 3645 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: 1.0259. Min Range: -1.0259

Max Act: 1.0259. Min Act: -0.0000

Data Index: 236635 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1201814 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6675. Min Act: -0.0000

Data Index: 937309 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6676. Min Act: -0.0000

Data Index: 740985 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6637. Min Act: -0.0000

Data Index: 193599 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6002. Min Act: -0.0000

Data Index: 76039 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6344. Min Act: -0.0000

Data Index: 1138592 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.5880. Min Act: -0.0000

Data Index: 265777 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6050. Min Act: -0.0000

Data Index: 361378 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1353574 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6163. Min Act: -0.0000

Data Index: 724780 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6071. Min Act: -0.0000

Data Index: 962471 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.5730. Min Act: -0.0000

Data Index: 630111 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1186881 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1258914 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.5578. Min Act: -0.0000

Data Index: 534810 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.5774. Min Act: -0.0000

Data Index: 550778 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.5243. Min Act: -0.0000

Data Index: 86024 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.5256. Min Act: -0.0000

Data Index: 478884 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.5571. Min Act: -0.0000

Data Index: 324766 (C4 (Web Text))

Max Activating Token Index: 157