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

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

Neuron 5510 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0015. Min Range: -1.0015

Max Act: 1.0015. Min Act: -0.0001

Data Index: 853345 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7646. Min Act: -0.0001

Data Index: 949914 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.8029. Min Act: -0.0001

Data Index: 1342861 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7215. Min Act: -0.0001

Data Index: 977983 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1068047 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1021814 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7512. Min Act: -0.0001

Data Index: 1117612 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1278276 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.6414. Min Act: -0.0000

Data Index: 470146 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5485. Min Act: -0.0000

Data Index: 165275 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1317727 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.6412. Min Act: -0.0000

Data Index: 927960 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5976. Min Act: -0.0000

Data Index: 368014 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.6288. Min Act: -0.0000

Data Index: 910056 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1325852 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1322439 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1247734 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.6030. Min Act: -0.0001

Data Index: 1254779 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5853. Min Act: -0.0001

Data Index: 397605 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1023632 (C4 (Web Text))

Max Activating Token Index: 352