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

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

Neuron 5718 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.8840. Min Act: -0.0000

Data Index: 174857 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.6254. Min Act: -0.0000

Data Index: 523532 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.7611. Min Act: -0.0000

Data Index: 426355 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.8701. Min Act: -0.0000

Data Index: 671711 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.6982. Min Act: -0.0000

Data Index: 103046 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.4784. Min Act: -0.0000

Data Index: 198190 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.6397. Min Act: -0.0000

Data Index: 1328371 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.5098. Min Act: -0.0000

Data Index: 786616 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.4867. Min Act: -0.0000

Data Index: 514543 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.3083. Min Act: -0.0000

Data Index: 567266 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.2729. Min Act: -0.0000

Data Index: 1341140 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.1011. Min Act: -0.0000

Data Index: 291512 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.2341. Min Act: -0.0000

Data Index: 474305 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.2455. Min Act: -0.0000

Data Index: 1155203 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.2109. Min Act: -0.0000

Data Index: 992373 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.1873. Min Act: -0.0000

Data Index: 1222272 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.3445. Min Act: -0.0000

Data Index: 1314365 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.1183. Min Act: -0.0000

Data Index: 780947 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.1418. Min Act: -0.0000

Data Index: 85660 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 5.8840. Min Range: -5.8840

Max Act: 5.1267. Min Act: -0.0000

Data Index: 1175414 (C4 (Web Text))

Max Activating Token Index: 192