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

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

Neuron 4825 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: 0.0872. Min Range: -0.0872

Max Act: 0.0822. Min Act: -0.0002

Data Index: 338603 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1154651 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0727. Min Act: -0.0002

Data Index: 893049 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1188497 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0701. Min Act: -0.0002

Data Index: 900766 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0715. Min Act: -0.0002

Data Index: 458561 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0708. Min Act: -0.0002

Data Index: 168624 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0608. Min Act: -0.0002

Data Index: 402866 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0595. Min Act: -0.0002

Data Index: 57292 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1293451 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0626. Min Act: -0.0002

Data Index: 623813 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0603. Min Act: -0.0002

Data Index: 142364 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0595. Min Act: -0.0002

Data Index: 613397 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0566. Min Act: -0.0002

Data Index: 696581 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0537. Min Act: -0.0002

Data Index: 236014 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0577. Min Act: -0.0002

Data Index: 135203 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0583. Min Act: -0.0002

Data Index: 235359 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1309620 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0626. Min Act: -0.0002

Data Index: 64664 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0540. Min Act: -0.0002

Data Index: 73235 (C4 (Web Text))

Max Activating Token Index: 384