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

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

Neuron 616 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0572. Min Range: -3.0572

Max Act: 3.0193. Min Act: -0.0000

Data Index: 343641 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 3.0572. Min Range: -3.0572

Max Act: 3.0572. Min Act: -0.0000

Data Index: 229594 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.6818. Min Act: -0.0000

Data Index: 269194 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.5129. Min Act: -0.0000

Data Index: 1295236 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.3254. Min Act: -0.0000

Data Index: 765347 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.1940. Min Act: -0.0000

Data Index: 1479668 (Python Code)

Max Activating Token Index: 179

Text #6

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.2950. Min Act: -0.0000

Data Index: 1253922 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.0722. Min Act: -0.0000

Data Index: 1261711 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.0068. Min Act: -0.0000

Data Index: 1650794 (Python Code)

Max Activating Token Index: 284

Text #9

Max Range: 3.0572. Min Range: -3.0572

Max Act: 1.9930. Min Act: -0.0000

Data Index: 1043474 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.0852. Min Act: -0.0000

Data Index: 460683 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 3.0572. Min Range: -3.0572

Max Act: 1.9651. Min Act: -0.0000

Data Index: 628079 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 3.0572. Min Range: -3.0572

Max Act: 1.9418. Min Act: -0.0000

Data Index: 130793 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 3.0572. Min Range: -3.0572

Max Act: 1.8924. Min Act: -0.0000

Data Index: 101950 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 3.0572. Min Range: -3.0572

Max Act: 1.9796. Min Act: -0.0000

Data Index: 410648 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 3.0572. Min Range: -3.0572

Max Act: 1.9808. Min Act: -0.0000

Data Index: 1367798 (Python Code)

Max Activating Token Index: 279

Text #16

Max Range: 3.0572. Min Range: -3.0572

Max Act: 1.8568. Min Act: -0.0000

Data Index: 861489 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.0646. Min Act: -0.0000

Data Index: 930542 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 3.0572. Min Range: -3.0572

Max Act: 1.9186. Min Act: -0.0000

Data Index: 98888 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 3.0572. Min Range: -3.0572

Max Act: 1.7265. Min Act: -0.0000

Data Index: 1124302 (C4 (Web Text))

Max Activating Token Index: 95