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

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

Neuron 5047 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.7743. Min Act: -0.0000

Data Index: 973865 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5906. Min Act: -0.0000

Data Index: 231525 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.5518. Min Act: -0.0000

Data Index: 1437186 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.2812. Min Act: -0.0000

Data Index: 266165 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.4302. Min Act: -0.0000

Data Index: 1435101 (Python Code)

Max Activating Token Index: 931

Text #5

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.2579. Min Act: -0.0000

Data Index: 572763 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.3915. Min Act: -0.0000

Data Index: 345508 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.3057. Min Act: -0.0000

Data Index: 601020 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.2825. Min Act: -0.0000

Data Index: 242244 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1563348 (Python Code)

Max Activating Token Index: 948

Text #10

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.2187. Min Act: -0.0000

Data Index: 447957 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.2732. Min Act: -0.0000

Data Index: 729642 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.2628. Min Act: -0.0000

Data Index: 350851 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.1916. Min Act: -0.0000

Data Index: 463383 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.0512. Min Act: -0.0000

Data Index: 1643875 (Python Code)

Max Activating Token Index: 998

Text #15

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.1780. Min Act: -0.0000

Data Index: 99824 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1655420 (Python Code)

Max Activating Token Index: 13

Text #17

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.0991. Min Act: -0.0000

Data Index: 1111031 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.2057. Min Act: -0.0000

Data Index: 51615 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 1.7743. Min Range: -1.7743

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1176254 (C4 (Web Text))

Max Activating Token Index: 112