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

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

Neuron 4893 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: 1.6133. Min Range: -1.6133

Max Act: 1.6133. Min Act: -0.0000

Data Index: 276046 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0480. Min Act: -0.0000

Data Index: 734393 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0549. Min Act: -0.0000

Data Index: 543758 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.9393. Min Act: -0.0000

Data Index: 1327537 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1187263 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.8688. Min Act: -0.0000

Data Index: 70108 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.8469. Min Act: -0.0000

Data Index: 710448 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.8745. Min Act: -0.0000

Data Index: 920277 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1154761 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.8436. Min Act: -0.0000

Data Index: 685745 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.8120. Min Act: -0.0000

Data Index: 711786 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.8079. Min Act: -0.0000

Data Index: 994741 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.7854. Min Act: -0.0000

Data Index: 624021 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.7658. Min Act: -0.0000

Data Index: 719419 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.7896. Min Act: -0.0000

Data Index: 753539 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.7221. Min Act: 0.0000

Data Index: 1223521 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.7575. Min Act: -0.0000

Data Index: 957630 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.6873. Min Act: -0.0000

Data Index: 957450 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1080459 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.7250. Min Act: -0.0000

Data Index: 803661 (C4 (Web Text))

Max Activating Token Index: 12