Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4501 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.3013. Min Act: -0.0002

Data Index: 491528 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.2885. Min Act: -0.0002

Data Index: 381064 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.1415. Min Act: -0.0002

Data Index: 9510 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.1298. Min Act: -0.0002

Data Index: 218871 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.1756. Min Act: -0.0002

Data Index: 284918 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.1162. Min Act: -0.0002

Data Index: 198950 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0762. Min Act: -0.0002

Data Index: 832420 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.1057. Min Act: -0.0002

Data Index: 1276316 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0697. Min Act: -0.0002

Data Index: 1203568 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0254. Min Act: -0.0002

Data Index: 499162 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0503. Min Act: -0.0002

Data Index: 1048216 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0832. Min Act: -0.0002

Data Index: 1258751 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0466. Min Act: -0.0002

Data Index: 853299 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0382. Min Act: -0.0002

Data Index: 445353 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0418. Min Act: -0.0002

Data Index: 381532 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0340. Min Act: -0.0002

Data Index: 845542 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0011. Min Act: -0.0002

Data Index: 90246 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0203. Min Act: -0.0002

Data Index: 948854 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0128. Min Act: -0.0002

Data Index: 1103212 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.9802. Min Act: -0.0002

Data Index: 257587 (C4 (Web Text))

Max Activating Token Index: 618