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

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

Neuron 5624 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: 0.0455. Min Range: -0.0455

Max Act: 0.0455. Min Act: -0.0002

Data Index: 930874 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0421. Min Act: -0.0002

Data Index: 190586 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1187882 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0343. Min Act: -0.0002

Data Index: 600452 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0336. Min Act: -0.0002

Data Index: 402772 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0333. Min Act: -0.0003

Data Index: 284469 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0330. Min Act: -0.0002

Data Index: 146459 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0328. Min Act: -0.0002

Data Index: 972715 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0318. Min Act: -0.0002

Data Index: 454195 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1324608 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0320. Min Act: -0.0002

Data Index: 375136 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0321. Min Act: -0.0002

Data Index: 276415 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0318. Min Act: -0.0002

Data Index: 679014 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1166380 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1239374 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0311. Min Act: -0.0002

Data Index: 345565 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1131741 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0314. Min Act: -0.0002

Data Index: 670863 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1185303 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1023472 (C4 (Web Text))

Max Activating Token Index: 15