Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4370 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7090. Min Range: -2.7090

Max Act: 2.7090. Min Act: -0.0000

Data Index: 462444 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.9534. Min Act: -0.0000

Data Index: 242010 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.9208. Min Act: -0.0000

Data Index: 652704 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.5498. Min Act: -0.0000

Data Index: 869688 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.5113. Min Act: -0.0000

Data Index: 800125 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.5219. Min Act: -0.0000

Data Index: 1080340 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.5769. Min Act: -0.0000

Data Index: 592283 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.4791. Min Act: -0.0000

Data Index: 71451 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.5533. Min Act: -0.0000

Data Index: 1198768 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.3143. Min Act: -0.0000

Data Index: 742105 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.3189. Min Act: -0.0000

Data Index: 908306 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.2943. Min Act: -0.0000

Data Index: 1183702 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.1884. Min Act: -0.0000

Data Index: 330572 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.1766. Min Act: -0.0000

Data Index: 696968 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.1663. Min Act: -0.0000

Data Index: 793539 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.1579. Min Act: -0.0000

Data Index: 387003 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.0698. Min Act: -0.0000

Data Index: 776884 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.0521. Min Act: -0.0000

Data Index: 129855 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.0341. Min Act: -0.0000

Data Index: 63109 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 2.7090. Min Range: -2.7090

Max Act: 1.0865. Min Act: -0.0000

Data Index: 549209 (C4 (Web Text))

Max Activating Token Index: 880