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

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

Neuron 2551 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: 1.4187. Min Range: -1.4187

Max Act: 1.4187. Min Act: -0.0000

Data Index: 667183 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.1190. Min Act: -0.0000

Data Index: 1335470 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.0088. Min Act: -0.0000

Data Index: 973119 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.0180. Min Act: -0.0000

Data Index: 390632 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.9357. Min Act: -0.0000

Data Index: 1591201 (Python Code)

Max Activating Token Index: 646

Text #5

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1569037 (Python Code)

Max Activating Token Index: 502

Text #6

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1585521 (Python Code)

Max Activating Token Index: 865

Text #7

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1279341 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.9570. Min Act: -0.0000

Data Index: 58048 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.7320. Min Act: -0.0000

Data Index: 781037 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.9040. Min Act: -0.0000

Data Index: 43605 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1082849 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.9204. Min Act: -0.0000

Data Index: 135679 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8883. Min Act: -0.0000

Data Index: 1266177 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8810. Min Act: -0.0000

Data Index: 235495 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8563. Min Act: -0.0000

Data Index: 947748 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.9207. Min Act: -0.0000

Data Index: 753774 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8904. Min Act: -0.0000

Data Index: 613615 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8331. Min Act: -0.0000

Data Index: 1193319 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 1.4187. Min Range: -1.4187

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1194731 (C4 (Web Text))

Max Activating Token Index: 509