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

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

Neuron 1460 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: 0.9874. Min Range: -0.9874

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1415050 (Python Code)

Max Activating Token Index: 892

Text #1

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1468880 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1636020 (Python Code)

Max Activating Token Index: 241

Text #3

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1380527 (Python Code)

Max Activating Token Index: 93

Text #4

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1465919 (Python Code)

Max Activating Token Index: 92

Text #5

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1656377 (Python Code)

Max Activating Token Index: 505

Text #6

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1568486 (Python Code)

Max Activating Token Index: 435

Text #7

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1568604 (Python Code)

Max Activating Token Index: 205

Text #8

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1372141 (Python Code)

Max Activating Token Index: 180

Text #9

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8153. Min Act: 0.0000

Data Index: 1371255 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1572659 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1405285 (Python Code)

Max Activating Token Index: 913

Text #12

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1431785 (Python Code)

Max Activating Token Index: 418

Text #13

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1551727 (Python Code)

Max Activating Token Index: 982

Text #14

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1381814 (Python Code)

Max Activating Token Index: 488

Text #15

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1544177 (Python Code)

Max Activating Token Index: 339

Text #16

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7203. Min Act: -0.0000

Data Index: 1377683 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1567322 (Python Code)

Max Activating Token Index: 762

Text #18

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1501167 (Python Code)

Max Activating Token Index: 247

Text #19

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1546123 (Python Code)

Max Activating Token Index: 482