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

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

Neuron 2815 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: 0.6043. Min Range: -0.6043

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1061758 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1463955 (Python Code)

Max Activating Token Index: 621

Text #2

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1637702 (Python Code)

Max Activating Token Index: 341

Text #3

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1566549 (Python Code)

Max Activating Token Index: 272

Text #4

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1472354 (Python Code)

Max Activating Token Index: 877

Text #5

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1535741 (Python Code)

Max Activating Token Index: 847

Text #6

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1562613 (Python Code)

Max Activating Token Index: 175

Text #7

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4681. Min Act: -0.0000

Data Index: 1503845 (Python Code)

Max Activating Token Index: 679

Text #8

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1539800 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1424136 (Python Code)

Max Activating Token Index: 821

Text #10

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1523640 (Python Code)

Max Activating Token Index: 806

Text #11

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1504590 (Python Code)

Max Activating Token Index: 525

Text #12

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1425509 (Python Code)

Max Activating Token Index: 529

Text #13

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4122. Min Act: -0.0000

Data Index: 24182 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1605031 (Python Code)

Max Activating Token Index: 492

Text #15

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1488088 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1452973 (Python Code)

Max Activating Token Index: 760

Text #17

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1581657 (Python Code)

Max Activating Token Index: 695

Text #18

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1620506 (Python Code)

Max Activating Token Index: 193

Text #19

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1393810 (Python Code)

Max Activating Token Index: 1012