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

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

Neuron 1574 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7287. Min Act: -0.0000

Data Index: 284662 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7225. Min Act: -0.0000

Data Index: 596251 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7044. Min Act: -0.0000

Data Index: 528874 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7031. Min Act: -0.0000

Data Index: 917044 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1326208 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6599. Min Act: -0.0000

Data Index: 821296 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1347163 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6929. Min Act: -0.0000

Data Index: 493584 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1105298 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6504. Min Act: -0.0000

Data Index: 316489 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6677. Min Act: -0.0000

Data Index: 10696 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1301820 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6198. Min Act: -0.0000

Data Index: 523025 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1058152 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5986. Min Act: -0.0000

Data Index: 542440 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6247. Min Act: -0.0000

Data Index: 205080 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6194. Min Act: -0.0000

Data Index: 228130 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5848. Min Act: -0.0000

Data Index: 871964 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7081. Min Act: -0.0000

Data Index: 301459 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6337. Min Act: -0.0000

Data Index: 275750 (C4 (Web Text))

Max Activating Token Index: 137