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

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

Neuron 3503 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.9100. Min Act: -0.0002

Data Index: 686837 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8476. Min Act: -0.0002

Data Index: 746461 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7819. Min Act: -0.0002

Data Index: 232461 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8156. Min Act: -0.0002

Data Index: 1294423 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7870. Min Act: -0.0002

Data Index: 135188 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7400. Min Act: -0.0002

Data Index: 776161 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7833. Min Act: -0.0002

Data Index: 630712 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7235. Min Act: -0.0002

Data Index: 928943 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7629. Min Act: -0.0002

Data Index: 1108879 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7756. Min Act: -0.0002

Data Index: 854902 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6619. Min Act: -0.0002

Data Index: 898129 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6061. Min Act: -0.0002

Data Index: 1177930 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7018. Min Act: -0.0002

Data Index: 1210804 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7166. Min Act: -0.0002

Data Index: 706733 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6697. Min Act: -0.0002

Data Index: 59018 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7368. Min Act: -0.0002

Data Index: 981489 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6782. Min Act: -0.0002

Data Index: 371869 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7046. Min Act: -0.0002

Data Index: 77454 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6363. Min Act: -0.0002

Data Index: 384116 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6609. Min Act: -0.0002

Data Index: 619537 (C4 (Web Text))

Max Activating Token Index: 630