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

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

Neuron 4238 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: 3.7283. Min Range: -3.7283

Max Act: 3.7283. Min Act: -0.0000

Data Index: 962056 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 3.7283. Min Range: -3.7283

Max Act: 3.0677. Min Act: -0.0000

Data Index: 496956 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 3.7283. Min Range: -3.7283

Max Act: 3.1810. Min Act: -0.0000

Data Index: 1530106 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 3.7283. Min Range: -3.7283

Max Act: 3.2883. Min Act: -0.0000

Data Index: 1646629 (Python Code)

Max Activating Token Index: 899

Text #4

Max Range: 3.7283. Min Range: -3.7283

Max Act: 3.0933. Min Act: -0.0000

Data Index: 1590665 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 3.7283. Min Range: -3.7283

Max Act: 3.3959. Min Act: -0.0000

Data Index: 474388 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 3.7283. Min Range: -3.7283

Max Act: 3.0746. Min Act: -0.0000

Data Index: 18966 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 3.7283. Min Range: -3.7283

Max Act: 3.0608. Min Act: -0.0000

Data Index: 690868 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 3.7283. Min Range: -3.7283

Max Act: 2.7496. Min Act: -0.0000

Data Index: 1358013 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 3.7283. Min Range: -3.7283

Max Act: 2.8771. Min Act: -0.0000

Data Index: 239733 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 3.7283. Min Range: -3.7283

Max Act: 2.7463. Min Act: -0.0000

Data Index: 1289825 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 3.7283. Min Range: -3.7283

Max Act: 2.8341. Min Act: -0.0000

Data Index: 173512 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 3.7283. Min Range: -3.7283

Max Act: 2.5087. Min Act: -0.0000

Data Index: 362777 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 3.7283. Min Range: -3.7283

Max Act: 2.4956. Min Act: -0.0000

Data Index: 1155123 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 3.7283. Min Range: -3.7283

Max Act: 2.5887. Min Act: -0.0000

Data Index: 640479 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 3.7283. Min Range: -3.7283

Max Act: 2.7185. Min Act: -0.0000

Data Index: 302245 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 3.7283. Min Range: -3.7283

Max Act: 2.8311. Min Act: -0.0000

Data Index: 340098 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 3.7283. Min Range: -3.7283

Max Act: 2.5719. Min Act: -0.0000

Data Index: 467527 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 3.7283. Min Range: -3.7283

Max Act: 2.5015. Min Act: -0.0000

Data Index: 512428 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 3.7283. Min Range: -3.7283

Max Act: 2.5054. Min Act: -0.0000

Data Index: 1042414 (C4 (Web Text))

Max Activating Token Index: 453