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

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

Neuron 3819 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: 0.8615. Min Range: -0.8615

Max Act: 0.8615. Min Act: -0.0000

Data Index: 537859 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.8203. Min Act: -0.0000

Data Index: 981553 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.8075. Min Act: -0.0000

Data Index: 107970 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.7457. Min Act: -0.0000

Data Index: 293009 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1088959 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.6926. Min Act: -0.0000

Data Index: 764506 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.7140. Min Act: -0.0000

Data Index: 626890 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.7020. Min Act: -0.0000

Data Index: 364044 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1355605 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.6464. Min Act: -0.0000

Data Index: 76449 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1130073 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.6496. Min Act: -0.0000

Data Index: 845048 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1325287 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.6573. Min Act: -0.0000

Data Index: 585901 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1321087 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.6532. Min Act: -0.0000

Data Index: 286461 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.6560. Min Act: -0.0000

Data Index: 610928 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.6459. Min Act: -0.0000

Data Index: 429292 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1086428 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1267374 (C4 (Web Text))

Max Activating Token Index: 879