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

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

Neuron 1100 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2555. Min Range: -3.2555

Max Act: 3.2555. Min Act: -0.0001

Data Index: 324615 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 3.2555. Min Range: -3.2555

Max Act: 3.2495. Min Act: -0.0001

Data Index: 728172 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 3.2555. Min Range: -3.2555

Max Act: 3.1160. Min Act: -0.0001

Data Index: 138410 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.8073. Min Act: -0.0001

Data Index: 1030805 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.7241. Min Act: -0.0001

Data Index: 1063641 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.6671. Min Act: -0.0001

Data Index: 786844 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.6403. Min Act: -0.0001

Data Index: 768626 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.4559. Min Act: -0.0001

Data Index: 458620 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.3233. Min Act: -0.0001

Data Index: 839275 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.5835. Min Act: -0.0001

Data Index: 1086228 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.3743. Min Act: -0.0001

Data Index: 1064566 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.2029. Min Act: -0.0001

Data Index: 725353 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.4101. Min Act: -0.0001

Data Index: 131745 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.2187. Min Act: -0.0001

Data Index: 596888 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.2320. Min Act: -0.0001

Data Index: 459308 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.2086. Min Act: -0.0001

Data Index: 1217650 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.2103. Min Act: -0.0001

Data Index: 75268 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.2012. Min Act: -0.0001

Data Index: 6987 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.2082. Min Act: -0.0001

Data Index: 687660 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.0766. Min Act: -0.0001

Data Index: 384495 (C4 (Web Text))

Max Activating Token Index: 740