Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 875 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1405. Min Act: -0.0005

Data Index: 317557 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1360. Min Act: -0.0005

Data Index: 1226074 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1235. Min Act: -0.0005

Data Index: 1305756 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1171. Min Act: -0.0005

Data Index: 1028700 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1014. Min Act: -0.0005

Data Index: 248483 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1004. Min Act: -0.0005

Data Index: 35506 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1009. Min Act: -0.0005

Data Index: 442594 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0965. Min Act: -0.0005

Data Index: 592083 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0980. Min Act: -0.0005

Data Index: 1112734 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0928. Min Act: -0.0005

Data Index: 681436 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0891. Min Act: -0.0005

Data Index: 880289 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0930. Min Act: -0.0005

Data Index: 925281 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0928. Min Act: -0.0005

Data Index: 741365 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0887. Min Act: -0.0005

Data Index: 971180 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0921. Min Act: -0.0005

Data Index: 748928 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0913. Min Act: -0.0005

Data Index: 442837 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0974. Min Act: -0.0005

Data Index: 659952 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0885. Min Act: -0.0005

Data Index: 630433 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0826. Min Act: -0.0005

Data Index: 807295 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0884. Min Act: -0.0005

Data Index: 777341 (C4 (Web Text))

Max Activating Token Index: 723