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

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

Neuron 965 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.3519. Min Act: -0.0000

Data Index: 1180710 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.3083. Min Act: -0.0000

Data Index: 601683 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.1410. Min Act: -0.0000

Data Index: 408152 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.0109. Min Act: -0.0000

Data Index: 383404 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.0934. Min Act: -0.0000

Data Index: 378907 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.0189. Min Act: -0.0000

Data Index: 426573 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.0295. Min Act: 0.0000

Data Index: 1014623 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.9535. Min Act: -0.0000

Data Index: 552373 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 1.3519. Min Range: -1.3519

Max Act: 1.0025. Min Act: 0.0000

Data Index: 1258908 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.9800. Min Act: 0.0000

Data Index: 1065991 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1218635 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.9342. Min Act: 0.0000

Data Index: 128782 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.9108. Min Act: -0.0000

Data Index: 17095 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1080129 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.8018. Min Act: 0.0000

Data Index: 22713 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.8980. Min Act: 0.0000

Data Index: 525886 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1136319 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1104532 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1627954 (Python Code)

Max Activating Token Index: 578

Text #19

Max Range: 1.3519. Min Range: -1.3519

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1633599 (Python Code)

Max Activating Token Index: 116