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

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

Neuron 2791 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.6138. Min Act: -0.0000

Data Index: 797101 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 3.6138. Min Range: -3.6138

Max Act: 2.6731. Min Act: -0.0000

Data Index: 1078326 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 3.6138. Min Range: -3.6138

Max Act: 2.6015. Min Act: -0.0000

Data Index: 1519317 (Python Code)

Max Activating Token Index: 951

Text #3

Max Range: 3.6138. Min Range: -3.6138

Max Act: 1.9619. Min Act: -0.0000

Data Index: 1472658 (Python Code)

Max Activating Token Index: 707

Text #4

Max Range: 3.6138. Min Range: -3.6138

Max Act: 2.0198. Min Act: -0.0000

Data Index: 1443132 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 3.6138. Min Range: -3.6138

Max Act: 2.0270. Min Act: -0.0000

Data Index: 1537368 (Python Code)

Max Activating Token Index: 502

Text #6

Max Range: 3.6138. Min Range: -3.6138

Max Act: 1.7872. Min Act: -0.0000

Data Index: 1262519 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 3.6138. Min Range: -3.6138

Max Act: 1.8899. Min Act: -0.0000

Data Index: 1492824 (Python Code)

Max Activating Token Index: 627

Text #8

Max Range: 3.6138. Min Range: -3.6138

Max Act: 1.8798. Min Act: -0.0000

Data Index: 1363097 (Python Code)

Max Activating Token Index: 209

Text #9

Max Range: 3.6138. Min Range: -3.6138

Max Act: 2.0971. Min Act: -0.0000

Data Index: 1649673 (Python Code)

Max Activating Token Index: 614

Text #10

Max Range: 3.6138. Min Range: -3.6138

Max Act: 2.0907. Min Act: -0.0000

Data Index: 1502131 (Python Code)

Max Activating Token Index: 745

Text #11

Max Range: 3.6138. Min Range: -3.6138

Max Act: 2.0534. Min Act: -0.0000

Data Index: 1429744 (Python Code)

Max Activating Token Index: 553

Text #12

Max Range: 3.6138. Min Range: -3.6138

Max Act: 1.9633. Min Act: -0.0000

Data Index: 1654501 (Python Code)

Max Activating Token Index: 280

Text #13

Max Range: 3.6138. Min Range: -3.6138

Max Act: 1.9775. Min Act: -0.0000

Data Index: 1504678 (Python Code)

Max Activating Token Index: 471

Text #14

Max Range: 3.6138. Min Range: -3.6138

Max Act: 1.8288. Min Act: -0.0000

Data Index: 1414137 (Python Code)

Max Activating Token Index: 586

Text #15

Max Range: 3.6138. Min Range: -3.6138

Max Act: 1.8225. Min Act: -0.0000

Data Index: 203387 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 3.6138. Min Range: -3.6138

Max Act: 1.7130. Min Act: -0.0000

Data Index: 1500158 (Python Code)

Max Activating Token Index: 939

Text #17

Max Range: 3.6138. Min Range: -3.6138

Max Act: 1.8058. Min Act: -0.0000

Data Index: 1507051 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 3.6138. Min Range: -3.6138

Max Act: 1.7849. Min Act: -0.0000

Data Index: 1372089 (Python Code)

Max Activating Token Index: 652

Text #19

Max Range: 3.6138. Min Range: -3.6138

Max Act: 1.8630. Min Act: -0.0000

Data Index: 1568793 (Python Code)

Max Activating Token Index: 23