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

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

Neuron 4327 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1310806 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.5014. Min Act: -0.0000

Data Index: 317043 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.4523. Min Act: -0.0000

Data Index: 665700 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.4081. Min Act: -0.0000

Data Index: 277962 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.4118. Min Act: -0.0000

Data Index: 730649 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1551207 (Python Code)

Max Activating Token Index: 749

Text #6

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3910. Min Act: -0.0000

Data Index: 973987 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3537. Min Act: -0.0000

Data Index: 233442 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3778. Min Act: -0.0000

Data Index: 701479 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1449761 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1520956 (Python Code)

Max Activating Token Index: 649

Text #11

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1386848 (Python Code)

Max Activating Token Index: 941

Text #12

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1516455 (Python Code)

Max Activating Token Index: 532

Text #13

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1508565 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1405375 (Python Code)

Max Activating Token Index: 307

Text #15

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3066. Min Act: -0.0000

Data Index: 27195 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1467022 (Python Code)

Max Activating Token Index: 191

Text #17

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1518349 (Python Code)

Max Activating Token Index: 851

Text #18

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1556493 (Python Code)

Max Activating Token Index: 949

Text #19

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1463050 (Python Code)

Max Activating Token Index: 957