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

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

Neuron 5697 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2381. Min Range: -1.2381

Max Act: 1.2381. Min Act: -0.0000

Data Index: 1243963 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 1.2381. Min Range: -1.2381

Max Act: 1.0536. Min Act: -0.0000

Data Index: 95087 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.9931. Min Act: -0.0000

Data Index: 718761 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 1.2381. Min Range: -1.2381

Max Act: 1.0241. Min Act: -0.0000

Data Index: 1368916 (Python Code)

Max Activating Token Index: 873

Text #4

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1468789 (Python Code)

Max Activating Token Index: 599

Text #5

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8937. Min Act: -0.0000

Data Index: 984196 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1335028 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8208. Min Act: -0.0000

Data Index: 236756 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.9269. Min Act: -0.0000

Data Index: 510612 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1082239 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1385715 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1482855 (Python Code)

Max Activating Token Index: 956

Text #12

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1318373 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8097. Min Act: -0.0000

Data Index: 692143 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.7661. Min Act: -0.0000

Data Index: 539417 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8086. Min Act: -0.0000

Data Index: 796164 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.7662. Min Act: -0.0000

Data Index: 514559 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.7647. Min Act: -0.0000

Data Index: 185576 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1283608 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.7517. Min Act: -0.0000

Data Index: 859918 (C4 (Web Text))

Max Activating Token Index: 7