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

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

Neuron 1981 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.5113. Min Act: -0.0000

Data Index: 883752 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.4735. Min Act: -0.0000

Data Index: 1261691 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.4206. Min Act: -0.0000

Data Index: 56146 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.3949. Min Act: -0.0000

Data Index: 871963 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.4039. Min Act: -0.0000

Data Index: 389764 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.3637. Min Act: -0.0000

Data Index: 111864 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.3491. Min Act: -0.0000

Data Index: 810464 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.2990. Min Act: -0.0000

Data Index: 604047 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.1630. Min Act: -0.0000

Data Index: 1062678 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.1097. Min Act: -0.0000

Data Index: 587259 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.2175. Min Act: -0.0000

Data Index: 773025 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.3670. Min Act: -0.0000

Data Index: 684282 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.1884. Min Act: -0.0000

Data Index: 722864 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.2011. Min Act: -0.0000

Data Index: 685496 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.1713. Min Act: -0.0000

Data Index: 758513 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.3064. Min Act: -0.0000

Data Index: 259367 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 2.5113. Min Range: -2.5113

Max Act: 1.9660. Min Act: -0.0000

Data Index: 1022739 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.0698. Min Act: -0.0000

Data Index: 34146 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.0510. Min Act: -0.0000

Data Index: 1265317 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 2.5113. Min Range: -2.5113

Max Act: 2.0512. Min Act: -0.0000

Data Index: 1045549 (C4 (Web Text))

Max Activating Token Index: 10