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

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

Neuron 4956 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0160. Min Range: -2.0160

Max Act: 2.0160. Min Act: -0.0000

Data Index: 610918 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.8898. Min Act: -0.0000

Data Index: 1252743 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.7612. Min Act: -0.0000

Data Index: 781974 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.7333. Min Act: -0.0000

Data Index: 849002 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.6980. Min Act: -0.0000

Data Index: 476016 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.7729. Min Act: -0.0000

Data Index: 1026603 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.5326. Min Act: -0.0000

Data Index: 377103 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.5164. Min Act: -0.0000

Data Index: 1091962 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.5896. Min Act: -0.0000

Data Index: 1245953 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.6512. Min Act: -0.0000

Data Index: 1172115 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.3587. Min Act: -0.0000

Data Index: 1271359 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.4134. Min Act: -0.0000

Data Index: 685500 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.5608. Min Act: -0.0000

Data Index: 236204 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.6500. Min Act: -0.0000

Data Index: 616128 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.4603. Min Act: -0.0000

Data Index: 408379 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.4047. Min Act: -0.0000

Data Index: 1053608 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.3764. Min Act: -0.0000

Data Index: 22696 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.3562. Min Act: -0.0000

Data Index: 350635 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.2635. Min Act: -0.0000

Data Index: 91143 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 2.0160. Min Range: -2.0160

Max Act: 1.2929. Min Act: -0.0000

Data Index: 1198678 (C4 (Web Text))

Max Activating Token Index: 136