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

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

Neuron 4212 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: 0.0650. Min Range: -0.0650

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1025737 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1344758 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0524. Min Act: -0.0002

Data Index: 511958 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0490. Min Act: -0.0002

Data Index: 696889 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0475. Min Act: -0.0002

Data Index: 76347 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0468. Min Act: -0.0002

Data Index: 994697 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1502289 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0468. Min Act: -0.0002

Data Index: 124831 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0458. Min Act: -0.0002

Data Index: 847049 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0451. Min Act: -0.0002

Data Index: 199564 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0453. Min Act: -0.0002

Data Index: 624665 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0449. Min Act: -0.0002

Data Index: 3993 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0440. Min Act: -0.0002

Data Index: 97074 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0456. Min Act: -0.0002

Data Index: 543553 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0445. Min Act: -0.0002

Data Index: 911821 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0438. Min Act: -0.0002

Data Index: 22493 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0432. Min Act: -0.0002

Data Index: 659664 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0439. Min Act: -0.0002

Data Index: 580665 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0434. Min Act: -0.0002

Data Index: 592609 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0432. Min Act: -0.0002

Data Index: 546260 (C4 (Web Text))

Max Activating Token Index: 620