Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4633 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0913. Min Range: -1.0913

Max Act: 1.0913. Min Act: -0.0000

Data Index: 88835 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9111. Min Act: -0.0000

Data Index: 943148 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1027939 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9640. Min Act: -0.0000

Data Index: 420402 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8708. Min Act: -0.0000

Data Index: 238421 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1023613 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1204673 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1355648 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8081. Min Act: -0.0000

Data Index: 302521 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8308. Min Act: -0.0000

Data Index: 923244 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7635. Min Act: -0.0000

Data Index: 197433 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7731. Min Act: -0.0000

Data Index: 64527 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7894. Min Act: -0.0000

Data Index: 40678 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7515. Min Act: -0.0000

Data Index: 451171 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1149442 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1061328 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7770. Min Act: -0.0000

Data Index: 492342 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7900. Min Act: -0.0000

Data Index: 706274 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1066301 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7392. Min Act: -0.0000

Data Index: 599391 (C4 (Web Text))

Max Activating Token Index: 182