Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1755 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0814. Min Range: -2.0814

Max Act: 2.0814. Min Act: -0.0000

Data Index: 1619774 (Python Code)

Max Activating Token Index: 866

Text #1

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.7334. Min Act: -0.0001

Data Index: 1499715 (Python Code)

Max Activating Token Index: 840

Text #2

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.6781. Min Act: -0.0001

Data Index: 1406627 (Python Code)

Max Activating Token Index: 1001

Text #3

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.6654. Min Act: -0.0001

Data Index: 1426146 (Python Code)

Max Activating Token Index: 744

Text #4

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.7247. Min Act: -0.0001

Data Index: 1384912 (Python Code)

Max Activating Token Index: 895

Text #5

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.7955. Min Act: -0.0000

Data Index: 1386363 (Python Code)

Max Activating Token Index: 679

Text #6

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.6590. Min Act: -0.0001

Data Index: 1639250 (Python Code)

Max Activating Token Index: 946

Text #7

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.8094. Min Act: -0.0001

Data Index: 1379296 (Python Code)

Max Activating Token Index: 897

Text #8

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.4186. Min Act: -0.0001

Data Index: 1364385 (Python Code)

Max Activating Token Index: 819

Text #9

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.2909. Min Act: -0.0000

Data Index: 531900 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.3647. Min Act: -0.0000

Data Index: 1151537 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.2499. Min Act: -0.0000

Data Index: 554325 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.4317. Min Act: -0.0001

Data Index: 1561292 (Python Code)

Max Activating Token Index: 927

Text #13

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.3538. Min Act: -0.0000

Data Index: 1111074 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.2977. Min Act: -0.0000

Data Index: 1292742 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.3040. Min Act: -0.0000

Data Index: 305605 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.2581. Min Act: -0.0000

Data Index: 101364 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.2919. Min Act: -0.0000

Data Index: 583602 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.2405. Min Act: -0.0000

Data Index: 1441233 (Python Code)

Max Activating Token Index: 949

Text #19

Max Range: 2.0814. Min Range: -2.0814

Max Act: 1.2119. Min Act: -0.0000

Data Index: 1090074 (C4 (Web Text))

Max Activating Token Index: 629