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

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

Neuron 3137 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: 1.3158. Min Range: -1.3158

Max Act: 1.3158. Min Act: -0.0000

Data Index: 504909 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.2876. Min Act: -0.0000

Data Index: 842281 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.2097. Min Act: -0.0000

Data Index: 1206550 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1341519 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.1849. Min Act: -0.0000

Data Index: 985845 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.2644. Min Act: -0.0000

Data Index: 988080 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.2219. Min Act: -0.0000

Data Index: 160451 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.1219. Min Act: -0.0000

Data Index: 536483 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1099317 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.0031. Min Act: -0.0000

Data Index: 404724 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 1.3158. Min Range: -1.3158

Max Act: 0.9560. Min Act: -0.0000

Data Index: 164352 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.3158. Min Range: -1.3158

Max Act: 1.0204. Min Act: 0.0000

Data Index: 733468 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 1.3158. Min Range: -1.3158

Max Act: 0.9834. Min Act: -0.0000

Data Index: 544674 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.3158. Min Range: -1.3158

Max Act: 0.9247. Min Act: 0.0000

Data Index: 936511 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 1.3158. Min Range: -1.3158

Max Act: 0.9204. Min Act: -0.0000

Data Index: 324808 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 1.3158. Min Range: -1.3158

Max Act: 0.9473. Min Act: -0.0000

Data Index: 132151 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 1.3158. Min Range: -1.3158

Max Act: 0.9437. Min Act: -0.0000

Data Index: 447138 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 1.3158. Min Range: -1.3158

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1045313 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 1.3158. Min Range: -1.3158

Max Act: 0.9530. Min Act: -0.0000

Data Index: 363536 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 1.3158. Min Range: -1.3158

Max Act: 0.9266. Min Act: -0.0000

Data Index: 995316 (C4 (Web Text))

Max Activating Token Index: 625