Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 280 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0542. Min Act: -0.0003

Data Index: 314225 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0560. Min Act: -0.0003

Data Index: 7238 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0561. Min Act: -0.0003

Data Index: 378966 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0553. Min Act: -0.0003

Data Index: 951886 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0542. Min Act: -0.0003

Data Index: 556823 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0533. Min Act: -0.0003

Data Index: 330267 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0520. Min Act: -0.0003

Data Index: 404134 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0525. Min Act: -0.0003

Data Index: 753603 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1201453 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0517. Min Act: -0.0003

Data Index: 505727 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1198643 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0504. Min Act: -0.0003

Data Index: 209842 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0512. Min Act: -0.0003

Data Index: 687517 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0509. Min Act: -0.0003

Data Index: 3809 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0510. Min Act: -0.0003

Data Index: 762704 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0501. Min Act: -0.0004

Data Index: 428116 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0492. Min Act: -0.0004

Data Index: 944468 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0494. Min Act: -0.0003

Data Index: 556030 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0524. Min Act: -0.0004

Data Index: 470045 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0508. Min Act: -0.0003

Data Index: 592653 (C4 (Web Text))

Max Activating Token Index: 220