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

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

Neuron 4766 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0661. Min Range: -1.0661

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1636192 (Python Code)

Max Activating Token Index: 331

Text #1

Max Range: 1.0661. Min Range: -1.0661

Max Act: 1.0273. Min Act: -0.0000

Data Index: 367851 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 1.0661. Min Range: -1.0661

Max Act: 1.0040. Min Act: -0.0000

Data Index: 1385534 (Python Code)

Max Activating Token Index: 796

Text #3

Max Range: 1.0661. Min Range: -1.0661

Max Act: 1.0511. Min Act: -0.0000

Data Index: 1638327 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9282. Min Act: -0.0000

Data Index: 642196 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 1.0661. Min Range: -1.0661

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1586952 (Python Code)

Max Activating Token Index: 908

Text #6

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1459898 (Python Code)

Max Activating Token Index: 238

Text #7

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1412810 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9536. Min Act: -0.0000

Data Index: 1430862 (Python Code)

Max Activating Token Index: 82

Text #9

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9484. Min Act: -0.0000

Data Index: 583505 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1361685 (Python Code)

Max Activating Token Index: 320

Text #11

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1382448 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9441. Min Act: -0.0000

Data Index: 249521 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1634265 (Python Code)

Max Activating Token Index: 387

Text #14

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1633174 (Python Code)

Max Activating Token Index: 628

Text #15

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1635930 (Python Code)

Max Activating Token Index: 387

Text #16

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1596037 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1542859 (Python Code)

Max Activating Token Index: 352

Text #18

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1184138 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 1.0661. Min Range: -1.0661

Max Act: 0.9097. Min Act: -0.0000

Data Index: 883724 (C4 (Web Text))

Max Activating Token Index: 450