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

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

Neuron 3341 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: 0.1232. Min Range: -0.1232

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1227516 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1217. Min Act: -0.0001

Data Index: 772277 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1203. Min Act: -0.0001

Data Index: 849734 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1232. Min Act: -0.0001

Data Index: 80658 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1189. Min Act: -0.0001

Data Index: 867310 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1099390 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1080887 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0984. Min Act: -0.0001

Data Index: 658050 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1039. Min Act: -0.0001

Data Index: 827384 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1189550 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1512710 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1383279 (Python Code)

Max Activating Token Index: 818

Text #12

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1168210 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0982. Min Act: -0.0001

Data Index: 77850 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0910. Min Act: -0.0001

Data Index: 29488 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0846. Min Act: -0.0001

Data Index: 196171 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0815. Min Act: -0.0001

Data Index: 868082 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0912. Min Act: -0.0001

Data Index: 471616 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0895. Min Act: -0.0001

Data Index: 288005 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1451909 (Python Code)

Max Activating Token Index: 892