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

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

Neuron 2447 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: 1.0848. Min Range: -1.0848

Max Act: 1.0848. Min Act: -0.0002

Data Index: 1262281 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.0848. Min Range: -1.0848

Max Act: 1.0796. Min Act: -0.0002

Data Index: 214249 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 1.0848. Min Range: -1.0848

Max Act: 1.0300. Min Act: -0.0002

Data Index: 459591 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9971. Min Act: -0.0002

Data Index: 1542821 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9971. Min Act: -0.0002

Data Index: 1505874 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9971. Min Act: -0.0002

Data Index: 797417 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9653. Min Act: -0.0002

Data Index: 194417 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9437. Min Act: -0.0002

Data Index: 201053 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9351. Min Act: -0.0002

Data Index: 1360710 (Python Code)

Max Activating Token Index: 114

Text #9

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9361. Min Act: -0.0002

Data Index: 50016 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9155. Min Act: -0.0002

Data Index: 1628336 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9207. Min Act: -0.0002

Data Index: 1452096 (Python Code)

Max Activating Token Index: 95

Text #12

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9187. Min Act: -0.0002

Data Index: 311719 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8919. Min Act: -0.0002

Data Index: 1573822 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9140. Min Act: -0.0002

Data Index: 379537 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9359. Min Act: -0.0002

Data Index: 1654695 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9237. Min Act: -0.0002

Data Index: 1493162 (Python Code)

Max Activating Token Index: 42

Text #17

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9153. Min Act: -0.0002

Data Index: 1069861 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8990. Min Act: -0.0002

Data Index: 183750 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9032. Min Act: -0.0002

Data Index: 1342345 (C4 (Web Text))

Max Activating Token Index: 790