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

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

Neuron 5015 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0372. Min Range: -8.0372

Max Act: 7.9947. Min Act: -0.0000

Data Index: 479271 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 8.0372. Min Range: -8.0372

Max Act: 8.0372. Min Act: -0.0000

Data Index: 1146723 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 8.0372. Min Range: -8.0372

Max Act: 7.4740. Min Act: -0.0000

Data Index: 161042 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 8.0372. Min Range: -8.0372

Max Act: 7.0384. Min Act: -0.0000

Data Index: 1258037 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 8.0372. Min Range: -8.0372

Max Act: 7.3267. Min Act: -0.0000

Data Index: 1256818 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 8.0372. Min Range: -8.0372

Max Act: 7.0689. Min Act: -0.0000

Data Index: 643014 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 8.0372. Min Range: -8.0372

Max Act: 7.0766. Min Act: -0.0000

Data Index: 1346431 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 8.0372. Min Range: -8.0372

Max Act: 6.8111. Min Act: -0.0000

Data Index: 167453 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 8.0372. Min Range: -8.0372

Max Act: 7.1255. Min Act: -0.0000

Data Index: 1020261 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 8.0372. Min Range: -8.0372

Max Act: 6.5055. Min Act: -0.0000

Data Index: 1491502 (Python Code)

Max Activating Token Index: 734

Text #10

Max Range: 8.0372. Min Range: -8.0372

Max Act: 6.8807. Min Act: -0.0000

Data Index: 204242 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 8.0372. Min Range: -8.0372

Max Act: 6.8636. Min Act: -0.0000

Data Index: 825350 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 8.0372. Min Range: -8.0372

Max Act: 6.8727. Min Act: -0.0000

Data Index: 424948 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 8.0372. Min Range: -8.0372

Max Act: 6.6403. Min Act: -0.0000

Data Index: 83814 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 8.0372. Min Range: -8.0372

Max Act: 6.8669. Min Act: -0.0000

Data Index: 76889 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 8.0372. Min Range: -8.0372

Max Act: 6.5822. Min Act: -0.0000

Data Index: 825414 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 8.0372. Min Range: -8.0372

Max Act: 6.6720. Min Act: -0.0000

Data Index: 96504 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 8.0372. Min Range: -8.0372

Max Act: 6.6570. Min Act: -0.0000

Data Index: 938244 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 8.0372. Min Range: -8.0372

Max Act: 6.5690. Min Act: -0.0000

Data Index: 607851 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 8.0372. Min Range: -8.0372

Max Act: 6.6982. Min Act: -0.0000

Data Index: 1205457 (C4 (Web Text))

Max Activating Token Index: 644