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

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

Neuron 2807 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: 2.3807. Min Range: -2.3807

Max Act: 2.3807. Min Act: -0.0000

Data Index: 77540 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 2.3807. Min Range: -2.3807

Max Act: 2.0063. Min Act: -0.0000

Data Index: 912144 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 2.3807. Min Range: -2.3807

Max Act: 2.0900. Min Act: -0.0000

Data Index: 1274910 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 2.3807. Min Range: -2.3807

Max Act: 2.1739. Min Act: -0.0000

Data Index: 190032 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.9525. Min Act: -0.0000

Data Index: 668312 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 2.3807. Min Range: -2.3807

Max Act: 2.0441. Min Act: -0.0000

Data Index: 382939 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.9860. Min Act: -0.0000

Data Index: 159017 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.9588. Min Act: -0.0000

Data Index: 1245249 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.8121. Min Act: -0.0000

Data Index: 745615 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.8024. Min Act: -0.0000

Data Index: 308682 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.9030. Min Act: -0.0000

Data Index: 974969 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.7340. Min Act: -0.0000

Data Index: 1299895 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.7838. Min Act: -0.0000

Data Index: 214877 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.8739. Min Act: -0.0000

Data Index: 135432 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.8630. Min Act: -0.0000

Data Index: 1331263 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.7293. Min Act: -0.0000

Data Index: 156706 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.8100. Min Act: -0.0000

Data Index: 214651 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.7535. Min Act: -0.0000

Data Index: 289505 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.7330. Min Act: -0.0000

Data Index: 812979 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 2.3807. Min Range: -2.3807

Max Act: 1.7054. Min Act: -0.0000

Data Index: 791529 (C4 (Web Text))

Max Activating Token Index: 980