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

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

Neuron 4596 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: 1.1056. Min Range: -1.1056

Max Act: 1.1056. Min Act: -0.0000

Data Index: 1287277 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 1.1056. Min Range: -1.1056

Max Act: 1.0859. Min Act: -0.0000

Data Index: 347130 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 1.1056. Min Range: -1.1056

Max Act: 1.0124. Min Act: -0.0000

Data Index: 437068 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1203066 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.8230. Min Act: -0.0000

Data Index: 388784 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1174147 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.8082. Min Act: -0.0000

Data Index: 28043 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1320127 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.7602. Min Act: -0.0000

Data Index: 234726 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1204699 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.7521. Min Act: -0.0000

Data Index: 278896 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.7342. Min Act: -0.0000

Data Index: 212317 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.6464. Min Act: -0.0000

Data Index: 346693 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.6764. Min Act: -0.0000

Data Index: 598559 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.6710. Min Act: -0.0000

Data Index: 908832 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.6774. Min Act: -0.0000

Data Index: 734139 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.7974. Min Act: -0.0000

Data Index: 857444 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1149463 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1130371 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 1.1056. Min Range: -1.1056

Max Act: 0.6783. Min Act: -0.0000

Data Index: 865355 (C4 (Web Text))

Max Activating Token Index: 451