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

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

Neuron 4093 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.1763. Min Act: -0.0000

Data Index: 858900 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.1055. Min Act: -0.0000

Data Index: 869180 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0530. Min Act: -0.0000

Data Index: 575799 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9481. Min Act: -0.0000

Data Index: 358972 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0260. Min Act: -0.0000

Data Index: 676502 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9495. Min Act: -0.0000

Data Index: 445215 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9326. Min Act: -0.0000

Data Index: 343554 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1020460 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8635. Min Act: -0.0000

Data Index: 93955 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1060984 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8746. Min Act: -0.0000

Data Index: 126306 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8140. Min Act: -0.0000

Data Index: 278601 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.7848. Min Act: -0.0000

Data Index: 525716 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.7771. Min Act: -0.0000

Data Index: 361958 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8062. Min Act: -0.0000

Data Index: 328007 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1091845 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.7766. Min Act: -0.0000

Data Index: 593043 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1282478 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8076. Min Act: -0.0000

Data Index: 447973 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.8073. Min Act: -0.0000

Data Index: 99572 (C4 (Web Text))

Max Activating Token Index: 482