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

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

Neuron 5168 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2710. Min Range: -1.2710

Max Act: 1.2710. Min Act: -0.0000

Data Index: 1476659 (Python Code)

Max Activating Token Index: 119

Text #1

Max Range: 1.2710. Min Range: -1.2710

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1606176 (Python Code)

Max Activating Token Index: 439

Text #2

Max Range: 1.2710. Min Range: -1.2710

Max Act: 1.0595. Min Act: -0.0000

Data Index: 1003985 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 1.2710. Min Range: -1.2710

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1480413 (Python Code)

Max Activating Token Index: 128

Text #4

Max Range: 1.2710. Min Range: -1.2710

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1505413 (Python Code)

Max Activating Token Index: 97

Text #5

Max Range: 1.2710. Min Range: -1.2710

Max Act: 1.0782. Min Act: -0.0000

Data Index: 662623 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 1.2710. Min Range: -1.2710

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1598877 (Python Code)

Max Activating Token Index: 616

Text #7

Max Range: 1.2710. Min Range: -1.2710

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1595722 (Python Code)

Max Activating Token Index: 345

Text #8

Max Range: 1.2710. Min Range: -1.2710

Max Act: 0.9819. Min Act: -0.0000

Data Index: 1586612 (Python Code)

Max Activating Token Index: 905

Text #9

Max Range: 1.2710. Min Range: -1.2710

Max Act: 1.0277. Min Act: -0.0000

Data Index: 18653 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 1.2710. Min Range: -1.2710

Max Act: 1.0067. Min Act: -0.0000

Data Index: 254490 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 1.2710. Min Range: -1.2710

Max Act: 1.0068. Min Act: -0.0000

Data Index: 288881 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 1.2710. Min Range: -1.2710

Max Act: 0.9968. Min Act: -0.0000

Data Index: 44360 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 1.2710. Min Range: -1.2710

Max Act: 0.9959. Min Act: -0.0000

Data Index: 441578 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 1.2710. Min Range: -1.2710

Max Act: 0.9199. Min Act: -0.0000

Data Index: 226835 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 1.2710. Min Range: -1.2710

Max Act: 0.9137. Min Act: -0.0000

Data Index: 274922 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 1.2710. Min Range: -1.2710

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1389918 (Python Code)

Max Activating Token Index: 395

Text #17

Max Range: 1.2710. Min Range: -1.2710

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1636068 (Python Code)

Max Activating Token Index: 815

Text #18

Max Range: 1.2710. Min Range: -1.2710

Max Act: 0.8815. Min Act: -0.0000

Data Index: 664270 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.2710. Min Range: -1.2710

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1566038 (Python Code)

Max Activating Token Index: 763