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

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

Neuron 1693 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.8216. Min Act: -0.0000

Data Index: 1444131 (Python Code)

Max Activating Token Index: 331

Text #1

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.5797. Min Act: -0.0000

Data Index: 1539680 (Python Code)

Max Activating Token Index: 945

Text #2

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.1684. Min Act: -0.0000

Data Index: 1632220 (Python Code)

Max Activating Token Index: 336

Text #3

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.1843. Min Act: -0.0000

Data Index: 167158 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.1369. Min Act: -0.0000

Data Index: 387340 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.1318. Min Act: -0.0000

Data Index: 1543645 (Python Code)

Max Activating Token Index: 385

Text #6

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.1122. Min Act: -0.0000

Data Index: 159182 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.0833. Min Act: -0.0000

Data Index: 402157 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.2052. Min Act: -0.0000

Data Index: 1413189 (Python Code)

Max Activating Token Index: 44

Text #9

Max Range: 3.8216. Min Range: -3.8216

Max Act: 2.9303. Min Act: -0.0000

Data Index: 463253 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.0011. Min Act: -0.0000

Data Index: 218098 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 3.8216. Min Range: -3.8216

Max Act: 2.8904. Min Act: -0.0000

Data Index: 905731 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 3.8216. Min Range: -3.8216

Max Act: 2.8822. Min Act: -0.0000

Data Index: 205408 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 3.8216. Min Range: -3.8216

Max Act: 2.7214. Min Act: -0.0000

Data Index: 717492 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 3.8216. Min Range: -3.8216

Max Act: 2.8614. Min Act: -0.0000

Data Index: 844018 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 3.8216. Min Range: -3.8216

Max Act: 2.8565. Min Act: -0.0000

Data Index: 602951 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 3.8216. Min Range: -3.8216

Max Act: 2.8584. Min Act: -0.0000

Data Index: 650675 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 3.8216. Min Range: -3.8216

Max Act: 2.8510. Min Act: -0.0000

Data Index: 1603543 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 3.8216. Min Range: -3.8216

Max Act: 2.8458. Min Act: -0.0000

Data Index: 89580 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 3.8216. Min Range: -3.8216

Max Act: 2.6737. Min Act: -0.0000

Data Index: 1514719 (Python Code)

Max Activating Token Index: 481