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

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

Neuron 4767 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1199642 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.8085. Min Act: -0.0000

Data Index: 386109 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7580. Min Act: -0.0000

Data Index: 860205 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7604. Min Act: -0.0000

Data Index: 537978 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7816. Min Act: -0.0000

Data Index: 122139 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7534. Min Act: -0.0000

Data Index: 899751 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1028476 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7367. Min Act: -0.0000

Data Index: 57621 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.5405. Min Act: -0.0000

Data Index: 887912 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1006869 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1338641 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6956. Min Act: -0.0000

Data Index: 151788 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7256. Min Act: -0.0000

Data Index: 553535 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7008. Min Act: -0.0000

Data Index: 55607 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1332798 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6899. Min Act: -0.0000

Data Index: 41687 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6835. Min Act: -0.0000

Data Index: 547447 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1190052 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7047. Min Act: -0.0000

Data Index: 398523 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6524. Min Act: -0.0000

Data Index: 563395 (C4 (Web Text))

Max Activating Token Index: 915