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

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

Neuron 5414 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.9702. Min Act: -0.0002

Data Index: 1397705 (Python Code)

Max Activating Token Index: 709

Text #1

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.9436. Min Act: -0.0002

Data Index: 1431001 (Python Code)

Max Activating Token Index: 656

Text #2

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.9290. Min Act: -0.0002

Data Index: 1625373 (Python Code)

Max Activating Token Index: 208

Text #3

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.9079. Min Act: -0.0002

Data Index: 1543990 (Python Code)

Max Activating Token Index: 236

Text #4

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.8854. Min Act: -0.0002

Data Index: 680173 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.8361. Min Act: -0.0002

Data Index: 132924 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.8213. Min Act: -0.0002

Data Index: 575866 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.8003. Min Act: -0.0002

Data Index: 1637120 (Python Code)

Max Activating Token Index: 627

Text #8

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.7931. Min Act: -0.0002

Data Index: 32615 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.7723. Min Act: -0.0002

Data Index: 1390086 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.7634. Min Act: -0.0002

Data Index: 1165075 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.7610. Min Act: -0.0002

Data Index: 871748 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.7625. Min Act: -0.0002

Data Index: 1387775 (Python Code)

Max Activating Token Index: 840

Text #13

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.7299. Min Act: -0.0002

Data Index: 84424 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.7364. Min Act: -0.0002

Data Index: 1143799 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.7225. Min Act: -0.0002

Data Index: 1214520 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.7225. Min Act: -0.0002

Data Index: 199407 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.7225. Min Act: -0.0002

Data Index: 1148528 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.7225. Min Act: -0.0002

Data Index: 1003536 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.9702. Min Range: -0.9702

Max Act: 0.7225. Min Act: -0.0002

Data Index: 1338711 (C4 (Web Text))

Max Activating Token Index: 2