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

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

Neuron 2452 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2559. Min Range: -1.2559

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1408145 (Python Code)

Max Activating Token Index: 483

Text #1

Max Range: 1.2559. Min Range: -1.2559

Max Act: 1.0497. Min Act: -0.0000

Data Index: 1451750 (Python Code)

Max Activating Token Index: 393

Text #2

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1254625 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8950. Min Act: -0.0000

Data Index: 36237 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.9540. Min Act: -0.0000

Data Index: 352504 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.9082. Min Act: -0.0000

Data Index: 672586 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8894. Min Act: -0.0000

Data Index: 824173 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8569. Min Act: -0.0000

Data Index: 334032 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8543. Min Act: -0.0000

Data Index: 92661 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8251. Min Act: -0.0000

Data Index: 964302 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1464914 (Python Code)

Max Activating Token Index: 371

Text #11

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1498516 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1377319 (Python Code)

Max Activating Token Index: 627

Text #13

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1347966 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1553272 (Python Code)

Max Activating Token Index: 214

Text #15

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.6108. Min Act: -0.0000

Data Index: 960147 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1465049 (Python Code)

Max Activating Token Index: 800

Text #17

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1192834 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1505804 (Python Code)

Max Activating Token Index: 225

Text #19

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.5896. Min Act: -0.0000

Data Index: 422635 (C4 (Web Text))

Max Activating Token Index: 597