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

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

Neuron 5440 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1137995 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1333868 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0805. Min Act: -0.0001

Data Index: 948180 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0795. Min Act: -0.0001

Data Index: 632208 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0809. Min Act: -0.0001

Data Index: 802159 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1137861 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1355562 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0790. Min Act: -0.0001

Data Index: 749530 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0768. Min Act: -0.0001

Data Index: 616300 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0780. Min Act: -0.0001

Data Index: 697566 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0778. Min Act: -0.0001

Data Index: 239008 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0773. Min Act: -0.0001

Data Index: 673386 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0756. Min Act: -0.0001

Data Index: 385359 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0762. Min Act: -0.0001

Data Index: 663127 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0758. Min Act: -0.0001

Data Index: 120246 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0765. Min Act: -0.0001

Data Index: 376096 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0760. Min Act: -0.0001

Data Index: 595192 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0747. Min Act: -0.0002

Data Index: 999882 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0735. Min Act: -0.0001

Data Index: 978440 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0730. Min Act: -0.0001

Data Index: 300245 (C4 (Web Text))

Max Activating Token Index: 509