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

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

Neuron 3610 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 18.3070. Min Range: -18.3070

Max Act: 18.3070. Min Act: -0.0002

Data Index: 1598811 (Python Code)

Max Activating Token Index: 198

Text #1

Max Range: 18.3070. Min Range: -18.3070

Max Act: 17.3049. Min Act: -0.0002

Data Index: 1616954 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 18.3070. Min Range: -18.3070

Max Act: 17.0580. Min Act: -0.0002

Data Index: 1564067 (Python Code)

Max Activating Token Index: 557

Text #3

Max Range: 18.3070. Min Range: -18.3070

Max Act: 17.1735. Min Act: -0.0002

Data Index: 1523484 (Python Code)

Max Activating Token Index: 155

Text #4

Max Range: 18.3070. Min Range: -18.3070

Max Act: 16.9185. Min Act: -0.0002

Data Index: 1532445 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 18.3070. Min Range: -18.3070

Max Act: 16.9162. Min Act: -0.0002

Data Index: 1382426 (Python Code)

Max Activating Token Index: 211

Text #6

Max Range: 18.3070. Min Range: -18.3070

Max Act: 16.2907. Min Act: -0.0002

Data Index: 1589428 (Python Code)

Max Activating Token Index: 655

Text #7

Max Range: 18.3070. Min Range: -18.3070

Max Act: 16.6680. Min Act: -0.0002

Data Index: 1419834 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 18.3070. Min Range: -18.3070

Max Act: 16.5330. Min Act: -0.0002

Data Index: 1631286 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 18.3070. Min Range: -18.3070

Max Act: 16.3016. Min Act: -0.0002

Data Index: 1437428 (Python Code)

Max Activating Token Index: 747

Text #10

Max Range: 18.3070. Min Range: -18.3070

Max Act: 16.4251. Min Act: -0.0002

Data Index: 1526982 (Python Code)

Max Activating Token Index: 367

Text #11

Max Range: 18.3070. Min Range: -18.3070

Max Act: 16.2937. Min Act: -0.0002

Data Index: 1469380 (Python Code)

Max Activating Token Index: 260

Text #12

Max Range: 18.3070. Min Range: -18.3070

Max Act: 16.2846. Min Act: -0.0002

Data Index: 1387539 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 18.3070. Min Range: -18.3070

Max Act: 16.1688. Min Act: -0.0002

Data Index: 1474464 (Python Code)

Max Activating Token Index: 854

Text #14

Max Range: 18.3070. Min Range: -18.3070

Max Act: 16.0435. Min Act: -0.0002

Data Index: 1442156 (Python Code)

Max Activating Token Index: 660

Text #15

Max Range: 18.3070. Min Range: -18.3070

Max Act: 16.0423. Min Act: -0.0002

Data Index: 1393231 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 18.3070. Min Range: -18.3070

Max Act: 15.9115. Min Act: -0.0002

Data Index: 1454949 (Python Code)

Max Activating Token Index: 345

Text #17

Max Range: 18.3070. Min Range: -18.3070

Max Act: 15.7831. Min Act: -0.0002

Data Index: 1564090 (Python Code)

Max Activating Token Index: 168

Text #18

Max Range: 18.3070. Min Range: -18.3070

Max Act: 15.9084. Min Act: -0.0002

Data Index: 1605292 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 18.3070. Min Range: -18.3070

Max Act: 15.7131. Min Act: -0.0002

Data Index: 1610804 (Python Code)

Max Activating Token Index: 392