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

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

Neuron 506 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: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1360640 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1366062 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1366645 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1365989 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1365988 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1365972 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1365903 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1360103 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1365372 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1365130 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1360180 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1364581 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1363908 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1363627 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1362607 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1359971 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1360777 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1366372 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1362002 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1361574 (Python Code)

Max Activating Token Index: 1