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

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

Neuron 3136 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.6797. Min Act: -0.0000

Data Index: 357755 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.4458. Min Act: -0.0000

Data Index: 170780 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.6054. Min Act: -0.0000

Data Index: 1215996 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.4961. Min Act: -0.0000

Data Index: 488152 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.4885. Min Act: -0.0000

Data Index: 891539 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.4883. Min Act: -0.0000

Data Index: 699789 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1194615 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.4535. Min Act: -0.0000

Data Index: 504336 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.4475. Min Act: -0.0000

Data Index: 1097953 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.4248. Min Act: -0.0000

Data Index: 665492 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.5195. Min Act: -0.0000

Data Index: 1193470 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.4261. Min Act: -0.0000

Data Index: 392519 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.4079. Min Act: -0.0000

Data Index: 79663 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.3939. Min Act: -0.0000

Data Index: 883968 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.3889. Min Act: -0.0000

Data Index: 924129 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.3694. Min Act: -0.0000

Data Index: 888130 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.3768. Min Act: -0.0000

Data Index: 540641 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.3731. Min Act: -0.0000

Data Index: 834845 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.3693. Min Act: -0.0000

Data Index: 488391 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 1.6797. Min Range: -1.6797

Max Act: 1.3642. Min Act: -0.0000

Data Index: 700490 (C4 (Web Text))

Max Activating Token Index: 540