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

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

Neuron 946 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.8739. Min Act: -0.0001

Data Index: 1249902 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.8948. Min Act: -0.0001

Data Index: 366945 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 1.0074. Min Range: -1.0074

Max Act: 1.0074. Min Act: -0.0001

Data Index: 462727 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.8030. Min Act: -0.0001

Data Index: 848870 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7904. Min Act: -0.0001

Data Index: 893422 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6947. Min Act: -0.0001

Data Index: 223251 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6692. Min Act: -0.0001

Data Index: 282301 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6922. Min Act: -0.0001

Data Index: 94082 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6706. Min Act: -0.0001

Data Index: 493524 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6506. Min Act: -0.0001

Data Index: 424441 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6295. Min Act: -0.0001

Data Index: 846512 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.5964. Min Act: -0.0001

Data Index: 483496 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6703. Min Act: -0.0001

Data Index: 887074 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6771. Min Act: -0.0001

Data Index: 794512 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6060. Min Act: -0.0001

Data Index: 578313 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.5827. Min Act: -0.0001

Data Index: 1586553 (Python Code)

Max Activating Token Index: 919

Text #16

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.5352. Min Act: -0.0001

Data Index: 187951 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.5627. Min Act: -0.0001

Data Index: 63386 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.5510. Min Act: -0.0001

Data Index: 471879 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6300. Min Act: -0.0001

Data Index: 860245 (C4 (Web Text))

Max Activating Token Index: 703