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

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

Neuron 4980 in Layer 1

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: 0.0997. Min Range: -0.0997

Max Act: 0.0997. Min Act: -0.0002

Data Index: 39557 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0932. Min Act: -0.0002

Data Index: 15591 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0945. Min Act: -0.0002

Data Index: 891707 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0885. Min Act: -0.0002

Data Index: 872801 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0850. Min Act: -0.0002

Data Index: 48586 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1171602 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0879. Min Act: -0.0002

Data Index: 502375 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0893. Min Act: -0.0002

Data Index: 330205 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0872. Min Act: -0.0002

Data Index: 418902 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0855. Min Act: -0.0002

Data Index: 178905 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1270367 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1130431 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1349669 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0805. Min Act: -0.0002

Data Index: 986994 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0797. Min Act: -0.0002

Data Index: 783551 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0817. Min Act: -0.0002

Data Index: 319291 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0810. Min Act: -0.0002

Data Index: 429986 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0806. Min Act: -0.0002

Data Index: 32735 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0805. Min Act: -0.0002

Data Index: 405226 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0774. Min Act: -0.0002

Data Index: 825623 (C4 (Web Text))

Max Activating Token Index: 58