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

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

Neuron 4720 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: 2.1000. Min Range: -2.1000

Max Act: 2.1000. Min Act: -0.0000

Data Index: 828779 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.8037. Min Act: -0.0000

Data Index: 1216755 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.7699. Min Act: -0.0000

Data Index: 1323097 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.6967. Min Act: -0.0000

Data Index: 215534 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.7708. Min Act: -0.0000

Data Index: 981436 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.7603. Min Act: -0.0000

Data Index: 988671 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.6254. Min Act: -0.0000

Data Index: 853683 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.4173. Min Act: -0.0000

Data Index: 443784 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.4905. Min Act: -0.0000

Data Index: 215409 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.5013. Min Act: -0.0000

Data Index: 1096930 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.5298. Min Act: -0.0000

Data Index: 817443 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.4832. Min Act: -0.0000

Data Index: 262617 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.3260. Min Act: -0.0000

Data Index: 792597 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.4795. Min Act: -0.0000

Data Index: 62936 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.4870. Min Act: -0.0000

Data Index: 1182492 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.4545. Min Act: -0.0000

Data Index: 1307046 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1162397 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.3071. Min Act: -0.0000

Data Index: 411890 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.3534. Min Act: -0.0000

Data Index: 595071 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 2.1000. Min Range: -2.1000

Max Act: 1.4537. Min Act: -0.0000

Data Index: 1186736 (C4 (Web Text))

Max Activating Token Index: 29