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

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

Neuron 4914 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0945. Min Range: -2.0945

Max Act: 2.0945. Min Act: -0.0000

Data Index: 533078 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.9771. Min Act: -0.0000

Data Index: 681853 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 2.0945. Min Range: -2.0945

Max Act: 2.0144. Min Act: -0.0000

Data Index: 567202 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.9799. Min Act: -0.0000

Data Index: 397887 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.9883. Min Act: -0.0000

Data Index: 946463 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.9346. Min Act: -0.0000

Data Index: 422350 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.9414. Min Act: -0.0000

Data Index: 1335947 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.9213. Min Act: -0.0000

Data Index: 746707 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.7995. Min Act: -0.0000

Data Index: 562074 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.8023. Min Act: -0.0000

Data Index: 1374759 (Python Code)

Max Activating Token Index: 941

Text #10

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.7969. Min Act: -0.0000

Data Index: 1501834 (Python Code)

Max Activating Token Index: 227

Text #11

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.8776. Min Act: -0.0000

Data Index: 419685 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.8384. Min Act: -0.0000

Data Index: 1524130 (Python Code)

Max Activating Token Index: 698

Text #13

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.8412. Min Act: -0.0000

Data Index: 7109 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.8191. Min Act: -0.0000

Data Index: 1171751 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.8247. Min Act: -0.0000

Data Index: 524667 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.7473. Min Act: -0.0000

Data Index: 841366 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.7646. Min Act: -0.0000

Data Index: 984391 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.7536. Min Act: -0.0000

Data Index: 1563744 (Python Code)

Max Activating Token Index: 135

Text #19

Max Range: 2.0945. Min Range: -2.0945

Max Act: 1.6453. Min Act: -0.0000

Data Index: 313386 (C4 (Web Text))

Max Activating Token Index: 268