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

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

Neuron 436 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: 0.9438. Min Range: -0.9438

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1515034 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.9438. Min Act: -0.0000

Data Index: 1525254 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8980. Min Act: -0.0001

Data Index: 1566935 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8791. Min Act: -0.0001

Data Index: 1595852 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8744. Min Act: -0.0001

Data Index: 1573738 (Python Code)

Max Activating Token Index: 216

Text #5

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1632485 (Python Code)

Max Activating Token Index: 73

Text #6

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8750. Min Act: -0.0001

Data Index: 1461271 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8724. Min Act: -0.0001

Data Index: 1519233 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8625. Min Act: -0.0001

Data Index: 1428897 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8833. Min Act: -0.0001

Data Index: 1544524 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1457447 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8123. Min Act: -0.0001

Data Index: 1597395 (Python Code)

Max Activating Token Index: 110

Text #12

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8070. Min Act: -0.0001

Data Index: 1404318 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7447. Min Act: -0.0001

Data Index: 1375714 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8233. Min Act: -0.0001

Data Index: 1464183 (Python Code)

Max Activating Token Index: 231

Text #15

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1570986 (Python Code)

Max Activating Token Index: 245

Text #16

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8415. Min Act: -0.0001

Data Index: 1449395 (Python Code)

Max Activating Token Index: 760

Text #17

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1402679 (Python Code)

Max Activating Token Index: 211

Text #18

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1414812 (Python Code)

Max Activating Token Index: 204

Text #19

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7251. Min Act: -0.0001

Data Index: 1549938 (Python Code)

Max Activating Token Index: 735