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

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

Neuron 5074 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.9976. Min Act: -0.0000

Data Index: 1205998 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.7856. Min Act: -0.0000

Data Index: 360534 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.7315. Min Act: -0.0000

Data Index: 1185469 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.5870. Min Act: -0.0000

Data Index: 1215052 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.6179. Min Act: -0.0000

Data Index: 1210631 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.4705. Min Act: -0.0000

Data Index: 933673 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.4532. Min Act: -0.0000

Data Index: 957336 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.5078. Min Act: -0.0000

Data Index: 486814 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.5482. Min Act: -0.0000

Data Index: 928675 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.4824. Min Act: -0.0000

Data Index: 777451 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.4226. Min Act: -0.0000

Data Index: 532452 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.4690. Min Act: -0.0000

Data Index: 1057920 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.4463. Min Act: -0.0000

Data Index: 1310021 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.3673. Min Act: -0.0000

Data Index: 1356684 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.3858. Min Act: -0.0000

Data Index: 799776 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.3003. Min Act: -0.0000

Data Index: 404206 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.3362. Min Act: -0.0000

Data Index: 1180879 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.2856. Min Act: 0.0000

Data Index: 479679 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.4286. Min Act: -0.0000

Data Index: 68011 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.3875. Min Act: -0.0000

Data Index: 1044236 (C4 (Web Text))

Max Activating Token Index: 1009