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

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

Neuron 64 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.4163. Min Act: -0.0001

Data Index: 1374914 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3468. Min Act: -0.0001

Data Index: 1369568 (Python Code)

Max Activating Token Index: 42

Text #2

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3346. Min Act: -0.0001

Data Index: 1531565 (Python Code)

Max Activating Token Index: 142

Text #3

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3426. Min Act: -0.0001

Data Index: 1378204 (Python Code)

Max Activating Token Index: 157

Text #4

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3260. Min Act: -0.0001

Data Index: 1544170 (Python Code)

Max Activating Token Index: 612

Text #5

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3159. Min Act: -0.0001

Data Index: 1466164 (Python Code)

Max Activating Token Index: 1002

Text #6

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3260. Min Act: -0.0001

Data Index: 1530706 (Python Code)

Max Activating Token Index: 48

Text #7

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3014. Min Act: -0.0001

Data Index: 1497358 (Python Code)

Max Activating Token Index: 1017

Text #8

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2929. Min Act: -0.0001

Data Index: 1486755 (Python Code)

Max Activating Token Index: 187

Text #9

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2987. Min Act: -0.0001

Data Index: 1515780 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2896. Min Act: -0.0001

Data Index: 1635505 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3106. Min Act: -0.0001

Data Index: 1530563 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2971. Min Act: -0.0001

Data Index: 1429712 (Python Code)

Max Activating Token Index: 263

Text #13

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2902. Min Act: -0.0001

Data Index: 1502333 (Python Code)

Max Activating Token Index: 164

Text #14

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3039. Min Act: -0.0001

Data Index: 1590422 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3120. Min Act: -0.0001

Data Index: 1385086 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2901. Min Act: -0.0001

Data Index: 1524419 (Python Code)

Max Activating Token Index: 998

Text #17

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2890. Min Act: -0.0001

Data Index: 1603016 (Python Code)

Max Activating Token Index: 155

Text #18

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2652. Min Act: -0.0001

Data Index: 1362023 (Python Code)

Max Activating Token Index: 175

Text #19

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2719. Min Act: -0.0001

Data Index: 1644681 (Python Code)

Max Activating Token Index: 290