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

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

Neuron 3795 in Layer 0

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: 0.3738. Min Range: -0.3738

Max Act: 0.3738. Min Act: -0.0001

Data Index: 1515697 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3430. Min Act: -0.0001

Data Index: 1395600 (Python Code)

Max Activating Token Index: 110

Text #2

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3479. Min Act: -0.0001

Data Index: 1412901 (Python Code)

Max Activating Token Index: 35

Text #3

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3307. Min Act: -0.0002

Data Index: 1624564 (Python Code)

Max Activating Token Index: 328

Text #4

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3217. Min Act: -0.0002

Data Index: 1378073 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3192. Min Act: -0.0001

Data Index: 1502191 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3224. Min Act: -0.0002

Data Index: 1508515 (Python Code)

Max Activating Token Index: 187

Text #7

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3223. Min Act: -0.0001

Data Index: 1432771 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3167. Min Act: -0.0001

Data Index: 1636880 (Python Code)

Max Activating Token Index: 140

Text #9

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3143. Min Act: -0.0001

Data Index: 1646575 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3169. Min Act: -0.0001

Data Index: 1432420 (Python Code)

Max Activating Token Index: 157

Text #11

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3161. Min Act: -0.0001

Data Index: 1361238 (Python Code)

Max Activating Token Index: 138

Text #12

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3066. Min Act: -0.0002

Data Index: 1573465 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3173. Min Act: -0.0001

Data Index: 1440127 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3189. Min Act: -0.0001

Data Index: 1609106 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3039. Min Act: -0.0001

Data Index: 1389167 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3071. Min Act: -0.0001

Data Index: 1516549 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3035. Min Act: -0.0001

Data Index: 1515337 (Python Code)

Max Activating Token Index: 281

Text #18

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3059. Min Act: -0.0001

Data Index: 1540357 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3048. Min Act: -0.0001

Data Index: 1496914 (Python Code)

Max Activating Token Index: 12