Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3757 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.2836. Min Act: -0.0001

Data Index: 696820 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.2245. Min Act: -0.0001

Data Index: 709314 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.2197. Min Act: -0.0001

Data Index: 331677 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.1564. Min Act: -0.0001

Data Index: 554503 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.1444. Min Act: -0.0001

Data Index: 779953 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9627. Min Act: -0.0001

Data Index: 407838 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0662. Min Act: -0.0001

Data Index: 362285 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0859. Min Act: -0.0001

Data Index: 216592 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0104. Min Act: -0.0001

Data Index: 533662 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.1000. Min Act: -0.0001

Data Index: 988085 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0891. Min Act: -0.0001

Data Index: 1082429 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0081. Min Act: -0.0001

Data Index: 682667 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0575. Min Act: -0.0001

Data Index: 1107313 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.8983. Min Act: -0.0001

Data Index: 108141 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0516. Min Act: -0.0001

Data Index: 1258611 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.0323. Min Act: -0.0001

Data Index: 68918 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9446. Min Act: -0.0001

Data Index: 963162 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.7824. Min Act: -0.0001

Data Index: 1144899 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9643. Min Act: -0.0001

Data Index: 1076810 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1302466 (C4 (Web Text))

Max Activating Token Index: 503