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

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

Neuron 3049 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: 1.7948. Min Range: -1.7948

Max Act: 1.7745. Min Act: -0.0002

Data Index: 1289166 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.7948. Min Act: -0.0002

Data Index: 767397 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.5967. Min Act: -0.0002

Data Index: 958625 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.5723. Min Act: -0.0002

Data Index: 84877 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.5698. Min Act: -0.0002

Data Index: 249283 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.5844. Min Act: -0.0002

Data Index: 65183 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.5200. Min Act: -0.0002

Data Index: 218635 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.5399. Min Act: -0.0002

Data Index: 824584 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.4165. Min Act: -0.0002

Data Index: 1086543 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.4648. Min Act: -0.0002

Data Index: 856485 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.4319. Min Act: -0.0002

Data Index: 984092 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.4780. Min Act: -0.0002

Data Index: 283393 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.4700. Min Act: -0.0002

Data Index: 1282072 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.3972. Min Act: -0.0002

Data Index: 195165 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.3825. Min Act: -0.0002

Data Index: 1257941 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.4148. Min Act: -0.0002

Data Index: 439056 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.4121. Min Act: -0.0002

Data Index: 344922 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.4162. Min Act: -0.0002

Data Index: 804064 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.3526. Min Act: -0.0002

Data Index: 195952 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.4067. Min Act: -0.0002

Data Index: 956680 (C4 (Web Text))

Max Activating Token Index: 23