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

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

Neuron 4076 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1311506 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1084158 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1021. Min Act: -0.0000

Data Index: 740041 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1034. Min Act: -0.0000

Data Index: 207800 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1022. Min Act: -0.0000

Data Index: 134437 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1189928 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0985. Min Act: -0.0000

Data Index: 882980 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0980. Min Act: -0.0000

Data Index: 411147 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0890. Min Act: -0.0000

Data Index: 50448 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0942. Min Act: -0.0000

Data Index: 625726 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1030384 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1192315 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0852. Min Act: -0.0000

Data Index: 297001 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0912. Min Act: -0.0000

Data Index: 727000 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0899. Min Act: -0.0000

Data Index: 356701 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1347454 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1192607 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0921. Min Act: -0.0000

Data Index: 256341 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0821. Min Act: -0.0000

Data Index: 967282 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1345616 (C4 (Web Text))

Max Activating Token Index: 254