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

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

Neuron 5086 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9683. Min Range: -3.9683

Max Act: 3.9683. Min Act: -0.0000

Data Index: 823774 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 3.9683. Min Range: -3.9683

Max Act: 3.3688. Min Act: -0.0000

Data Index: 1233861 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 3.9683. Min Range: -3.9683

Max Act: 3.2962. Min Act: -0.0000

Data Index: 15213 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 3.9683. Min Range: -3.9683

Max Act: 3.1397. Min Act: -0.0000

Data Index: 176793 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 3.9683. Min Range: -3.9683

Max Act: 3.1718. Min Act: -0.0000

Data Index: 507198 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 3.9683. Min Range: -3.9683

Max Act: 3.1949. Min Act: -0.0000

Data Index: 502784 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 3.9683. Min Range: -3.9683

Max Act: 3.0440. Min Act: -0.0000

Data Index: 1036393 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.9671. Min Act: -0.0000

Data Index: 1305720 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.9318. Min Act: -0.0000

Data Index: 1264498 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.7210. Min Act: -0.0000

Data Index: 1319705 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.9297. Min Act: -0.0000

Data Index: 836446 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.6192. Min Act: -0.0000

Data Index: 204532 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.6392. Min Act: -0.0000

Data Index: 1058388 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.6224. Min Act: -0.0000

Data Index: 581702 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.5740. Min Act: -0.0000

Data Index: 520757 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.3274. Min Act: -0.0000

Data Index: 937412 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.5333. Min Act: -0.0000

Data Index: 395400 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.4432. Min Act: -0.0000

Data Index: 351314 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.4172. Min Act: -0.0000

Data Index: 595047 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 3.9683. Min Range: -3.9683

Max Act: 2.3095. Min Act: -0.0000

Data Index: 275740 (C4 (Web Text))

Max Activating Token Index: 1007