Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2175 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1478154 (Python Code)

Max Activating Token Index: 666

Text #1

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4641. Min Act: 0.0000

Data Index: 1511988 (Python Code)

Max Activating Token Index: 95

Text #2

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1611090 (Python Code)

Max Activating Token Index: 120

Text #3

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1577358 (Python Code)

Max Activating Token Index: 685

Text #4

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1377384 (Python Code)

Max Activating Token Index: 721

Text #5

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3367. Min Act: 0.0000

Data Index: 1492136 (Python Code)

Max Activating Token Index: 118

Text #6

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3423. Min Act: 0.0000

Data Index: 1591858 (Python Code)

Max Activating Token Index: 568

Text #7

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3328. Min Act: 0.0001

Data Index: 1471756 (Python Code)

Max Activating Token Index: 207

Text #8

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1402565 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3156. Min Act: 0.0000

Data Index: 1529383 (Python Code)

Max Activating Token Index: 461

Text #10

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3204. Min Act: 0.0000

Data Index: 1379912 (Python Code)

Max Activating Token Index: 548

Text #11

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3172. Min Act: 0.0000

Data Index: 1543803 (Python Code)

Max Activating Token Index: 641

Text #12

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1062218 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1563539 (Python Code)

Max Activating Token Index: 237

Text #14

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1530950 (Python Code)

Max Activating Token Index: 218

Text #15

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3094. Min Act: 0.0000

Data Index: 1599077 (Python Code)

Max Activating Token Index: 390

Text #16

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1560192 (Python Code)

Max Activating Token Index: 846

Text #17

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.2992. Min Act: -0.0001

Data Index: 1622891 (Python Code)

Max Activating Token Index: 683

Text #18

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3091. Min Act: 0.0000

Data Index: 1496876 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1588105 (Python Code)

Max Activating Token Index: 878