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

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

Neuron 2947 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 7.0881. Min Range: -7.0881

Max Act: 7.0881. Min Act: -0.0001

Data Index: 895005 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 7.0881. Min Range: -7.0881

Max Act: 6.1532. Min Act: -0.0001

Data Index: 338117 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 7.0881. Min Range: -7.0881

Max Act: 6.3027. Min Act: -0.0001

Data Index: 286374 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 7.0881. Min Range: -7.0881

Max Act: 6.2045. Min Act: -0.0001

Data Index: 1192016 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 7.0881. Min Range: -7.0881

Max Act: 5.9920. Min Act: -0.0001

Data Index: 1075807 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 7.0881. Min Range: -7.0881

Max Act: 6.1473. Min Act: -0.0001

Data Index: 1318851 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 7.0881. Min Range: -7.0881

Max Act: 6.6400. Min Act: -0.0001

Data Index: 923900 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 7.0881. Min Range: -7.0881

Max Act: 6.1667. Min Act: -0.0001

Data Index: 1608900 (Python Code)

Max Activating Token Index: 719

Text #8

Max Range: 7.0881. Min Range: -7.0881

Max Act: 5.8292. Min Act: -0.0001

Data Index: 612975 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 7.0881. Min Range: -7.0881

Max Act: 5.9200. Min Act: -0.0001

Data Index: 180379 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 7.0881. Min Range: -7.0881

Max Act: 5.8203. Min Act: -0.0001

Data Index: 593601 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 7.0881. Min Range: -7.0881

Max Act: 5.8079. Min Act: -0.0001

Data Index: 429342 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 7.0881. Min Range: -7.0881

Max Act: 6.1047. Min Act: -0.0001

Data Index: 326384 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 7.0881. Min Range: -7.0881

Max Act: 5.8745. Min Act: -0.0001

Data Index: 166887 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 7.0881. Min Range: -7.0881

Max Act: 5.4298. Min Act: -0.0001

Data Index: 485163 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 7.0881. Min Range: -7.0881

Max Act: 5.5785. Min Act: -0.0001

Data Index: 702834 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 7.0881. Min Range: -7.0881

Max Act: 5.4036. Min Act: -0.0001

Data Index: 346742 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 7.0881. Min Range: -7.0881

Max Act: 5.5097. Min Act: -0.0001

Data Index: 856957 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 7.0881. Min Range: -7.0881

Max Act: 5.5560. Min Act: -0.0001

Data Index: 387483 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 7.0881. Min Range: -7.0881

Max Act: 4.6929. Min Act: -0.0001

Data Index: 104514 (C4 (Web Text))

Max Activating Token Index: 1023