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

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

Neuron 140 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: 0.3557. Min Range: -0.3557

Max Act: 0.3557. Min Act: -0.0000

Data Index: 342025 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.3487. Min Act: -0.0000

Data Index: 606437 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.3303. Min Act: -0.0001

Data Index: 715847 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.3178. Min Act: -0.0000

Data Index: 930712 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1043342 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.3195. Min Act: -0.0000

Data Index: 662815 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.3006. Min Act: -0.0000

Data Index: 390841 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.3093. Min Act: -0.0000

Data Index: 716053 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.3020. Min Act: -0.0000

Data Index: 618414 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.3118. Min Act: -0.0000

Data Index: 560443 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.3075. Min Act: -0.0000

Data Index: 181617 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.2933. Min Act: -0.0000

Data Index: 408493 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1295993 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.2925. Min Act: -0.0001

Data Index: 228110 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.2943. Min Act: -0.0000

Data Index: 567314 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.2995. Min Act: -0.0001

Data Index: 26374 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.2771. Min Act: -0.0000

Data Index: 600710 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1474006 (Python Code)

Max Activating Token Index: 542

Text #18

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.2746. Min Act: -0.0000

Data Index: 998556 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.3557. Min Range: -0.3557

Max Act: 0.2705. Min Act: -0.0000

Data Index: 1495149 (Python Code)

Max Activating Token Index: 745