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

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

Neuron 1499 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5425. Min Act: -0.0000

Data Index: 745195 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5421. Min Act: -0.0000

Data Index: 731466 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5342. Min Act: -0.0000

Data Index: 460716 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4934. Min Act: -0.0000

Data Index: 958904 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4247. Min Act: 0.0000

Data Index: 291725 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4387. Min Act: -0.0000

Data Index: 279434 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4151. Min Act: -0.0000

Data Index: 478243 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3809. Min Act: 0.0000

Data Index: 902161 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3810. Min Act: 0.0000

Data Index: 821624 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3767. Min Act: -0.0000

Data Index: 905527 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1058117 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1138606 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3875. Min Act: 0.0000

Data Index: 1062565 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3760. Min Act: -0.0000

Data Index: 194305 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3833. Min Act: -0.0000

Data Index: 228451 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3761. Min Act: 0.0000

Data Index: 1192656 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1055754 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1080203 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3790. Min Act: -0.0000

Data Index: 362193 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1191985 (C4 (Web Text))

Max Activating Token Index: 618