Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2518 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4651. Min Act: -0.0002

Data Index: 762974 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4628. Min Act: -0.0002

Data Index: 808144 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4906. Min Act: -0.0002

Data Index: 996410 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4571. Min Act: -0.0002

Data Index: 223731 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4402. Min Act: -0.0002

Data Index: 56118 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4423. Min Act: -0.0002

Data Index: 1262705 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4150. Min Act: -0.0002

Data Index: 1350825 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3708. Min Act: -0.0002

Data Index: 426439 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3874. Min Act: -0.0002

Data Index: 66885 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3902. Min Act: -0.0002

Data Index: 393892 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3559. Min Act: -0.0002

Data Index: 964574 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3678. Min Act: -0.0002

Data Index: 1001373 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3813. Min Act: -0.0002

Data Index: 1347278 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3525. Min Act: -0.0002

Data Index: 848643 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3266. Min Act: -0.0002

Data Index: 147195 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3668. Min Act: -0.0002

Data Index: 614823 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3529. Min Act: -0.0002

Data Index: 1289441 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3720. Min Act: -0.0002

Data Index: 741117 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3733. Min Act: -0.0002

Data Index: 1347692 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3458. Min Act: -0.0002

Data Index: 254142 (C4 (Web Text))

Max Activating Token Index: 924