Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1511 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.2237. Min Act: -0.0004

Data Index: 1462794 (Python Code)

Max Activating Token Index: 258

Text #1

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1782. Min Act: -0.0004

Data Index: 1452080 (Python Code)

Max Activating Token Index: 299

Text #2

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1111. Min Act: -0.0004

Data Index: 1598109 (Python Code)

Max Activating Token Index: 266

Text #3

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0942. Min Act: -0.0004

Data Index: 1594587 (Python Code)

Max Activating Token Index: 263

Text #4

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0351. Min Act: -0.0004

Data Index: 1528903 (Python Code)

Max Activating Token Index: 218

Text #5

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0639. Min Act: -0.0004

Data Index: 1631693 (Python Code)

Max Activating Token Index: 334

Text #6

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0583. Min Act: -0.0004

Data Index: 1600725 (Python Code)

Max Activating Token Index: 318

Text #7

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0894. Min Act: -0.0004

Data Index: 1568322 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0694. Min Act: -0.0004

Data Index: 1486671 (Python Code)

Max Activating Token Index: 701

Text #9

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0686. Min Act: -0.0004

Data Index: 1570838 (Python Code)

Max Activating Token Index: 525

Text #10

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0634. Min Act: -0.0004

Data Index: 1454754 (Python Code)

Max Activating Token Index: 469

Text #11

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0450. Min Act: -0.0004

Data Index: 1551995 (Python Code)

Max Activating Token Index: 423

Text #12

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0109. Min Act: -0.0004

Data Index: 1527625 (Python Code)

Max Activating Token Index: 540

Text #13

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0948. Min Act: -0.0004

Data Index: 1520379 (Python Code)

Max Activating Token Index: 367

Text #14

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0198. Min Act: -0.0004

Data Index: 1379011 (Python Code)

Max Activating Token Index: 467

Text #15

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0150. Min Act: -0.0004

Data Index: 1436316 (Python Code)

Max Activating Token Index: 488

Text #16

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0151. Min Act: -0.0004

Data Index: 1434822 (Python Code)

Max Activating Token Index: 664

Text #17

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0093. Min Act: -0.0004

Data Index: 1614290 (Python Code)

Max Activating Token Index: 270

Text #18

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9404. Min Act: -0.0004

Data Index: 1583001 (Python Code)

Max Activating Token Index: 390

Text #19

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9688. Min Act: -0.0004

Data Index: 1597697 (Python Code)

Max Activating Token Index: 473