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

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

Neuron 439 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4709. Min Range: -5.4709

Max Act: 5.4709. Min Act: -0.0000

Data Index: 1085312 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 5.4709. Min Range: -5.4709

Max Act: 5.4486. Min Act: -0.0000

Data Index: 1146980 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.8460. Min Act: -0.0000

Data Index: 703611 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.8815. Min Act: -0.0000

Data Index: 506053 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.8619. Min Act: -0.0000

Data Index: 450742 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.7760. Min Act: -0.0000

Data Index: 948681 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.4509. Min Act: -0.0000

Data Index: 778247 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.1306. Min Act: -0.0000

Data Index: 810677 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.4653. Min Act: -0.0000

Data Index: 415015 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.2460. Min Act: -0.0000

Data Index: 391431 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.2366. Min Act: -0.0000

Data Index: 673750 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.2095. Min Act: -0.0000

Data Index: 981147 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.0465. Min Act: -0.0000

Data Index: 793222 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.1863. Min Act: -0.0000

Data Index: 1060898 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.1504. Min Act: -0.0000

Data Index: 1291218 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 5.4709. Min Range: -5.4709

Max Act: 4.6568. Min Act: -0.0000

Data Index: 988562 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 5.4709. Min Range: -5.4709

Max Act: 3.9442. Min Act: -0.0000

Data Index: 255067 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 5.4709. Min Range: -5.4709

Max Act: 3.9730. Min Act: -0.0000

Data Index: 472570 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 5.4709. Min Range: -5.4709

Max Act: 3.9482. Min Act: -0.0000

Data Index: 806021 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 5.4709. Min Range: -5.4709

Max Act: 3.5927. Min Act: -0.0000

Data Index: 847791 (C4 (Web Text))

Max Activating Token Index: 121