Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1731 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1242. Min Act: -0.0006

Data Index: 871464 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1260. Min Act: -0.0006

Data Index: 677945 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1154. Min Act: -0.0006

Data Index: 700184 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1052. Min Act: -0.0006

Data Index: 341879 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1088. Min Act: -0.0006

Data Index: 205949 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1114. Min Act: -0.0006

Data Index: 640586 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1074. Min Act: -0.0006

Data Index: 1052950 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1076. Min Act: -0.0006

Data Index: 823248 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1051. Min Act: -0.0006

Data Index: 312048 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1040. Min Act: -0.0006

Data Index: 814746 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0997. Min Act: -0.0006

Data Index: 562198 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1076. Min Act: -0.0006

Data Index: 565753 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0977. Min Act: -0.0006

Data Index: 596078 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1058. Min Act: -0.0006

Data Index: 1358541 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0929. Min Act: -0.0006

Data Index: 560640 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1038. Min Act: -0.0006

Data Index: 691381 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0925. Min Act: -0.0006

Data Index: 635075 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0959. Min Act: -0.0006

Data Index: 956172 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1031. Min Act: -0.0006

Data Index: 78335 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0989. Min Act: -0.0006

Data Index: 824173 (C4 (Web Text))

Max Activating Token Index: 466