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

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

Neuron 3239 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3341. Min Act: -0.0001

Data Index: 763957 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1157364 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1491975 (Python Code)

Max Activating Token Index: 1022

Text #3

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1128954 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3234. Min Act: -0.0000

Data Index: 684834 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3190. Min Act: -0.0000

Data Index: 426769 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2832. Min Act: -0.0000

Data Index: 914568 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2662. Min Act: -0.0000

Data Index: 256906 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2596. Min Act: -0.0000

Data Index: 697422 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2586. Min Act: -0.0000

Data Index: 145232 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1219633 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1145591 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1281379 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1100910 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2584. Min Act: -0.0000

Data Index: 223969 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2587. Min Act: -0.0000

Data Index: 822411 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2373. Min Act: -0.0001

Data Index: 581306 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2895. Min Act: -0.0001

Data Index: 25939 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1220071 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2481. Min Act: -0.0000

Data Index: 396151 (C4 (Web Text))

Max Activating Token Index: 162