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

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

Neuron 5744 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1202401 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1511684 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 738033 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 286544 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 847492 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1006712 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1281984 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 790790 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 808557 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 834034 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1627184 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1338713 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1334344 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 222837 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1240012 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1403559 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 12749 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 602835 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 28628 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 214165 (C4 (Web Text))

Max Activating Token Index: 292