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

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

Neuron 1659 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: 1.0746. Min Range: -1.0746

Max Act: 1.0746. Min Act: -0.0000

Data Index: 57092 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.0746. Min Range: -1.0746

Max Act: 1.0011. Min Act: -0.0000

Data Index: 700895 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8207. Min Act: -0.0000

Data Index: 170809 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8106. Min Act: -0.0000

Data Index: 868213 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.7937. Min Act: -0.0000

Data Index: 472787 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.7180. Min Act: -0.0000

Data Index: 605896 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.7613. Min Act: -0.0000

Data Index: 644379 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1166043 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.7147. Min Act: -0.0000

Data Index: 518684 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6825. Min Act: -0.0000

Data Index: 184147 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6964. Min Act: -0.0000

Data Index: 552481 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6956. Min Act: -0.0000

Data Index: 869255 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.7260. Min Act: -0.0000

Data Index: 144499 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.7197. Min Act: -0.0000

Data Index: 797478 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6773. Min Act: -0.0000

Data Index: 487665 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1178889 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1476193 (Python Code)

Max Activating Token Index: 143

Text #17

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6758. Min Act: -0.0000

Data Index: 81157 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6654. Min Act: -0.0000

Data Index: 577410 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6709. Min Act: -0.0000

Data Index: 72390 (C4 (Web Text))

Max Activating Token Index: 473