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

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

Neuron 1696 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6881. Min Act: -0.0002

Data Index: 912355 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5151. Min Act: -0.0002

Data Index: 930547 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4926. Min Act: -0.0002

Data Index: 1142610 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4929. Min Act: -0.0002

Data Index: 1016620 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4443. Min Act: -0.0002

Data Index: 502595 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4660. Min Act: -0.0002

Data Index: 852758 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4719. Min Act: -0.0002

Data Index: 685176 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4722. Min Act: -0.0002

Data Index: 297448 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4505. Min Act: -0.0002

Data Index: 110361 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4481. Min Act: -0.0002

Data Index: 891772 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4298. Min Act: -0.0002

Data Index: 391933 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4335. Min Act: -0.0002

Data Index: 137383 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4498. Min Act: -0.0002

Data Index: 529921 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4362. Min Act: -0.0002

Data Index: 29332 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4611. Min Act: -0.0002

Data Index: 1069168 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4458. Min Act: -0.0002

Data Index: 356510 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4468. Min Act: -0.0002

Data Index: 933130 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4692. Min Act: -0.0002

Data Index: 425802 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4460. Min Act: -0.0002

Data Index: 435107 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4214. Min Act: -0.0002

Data Index: 210128 (C4 (Web Text))

Max Activating Token Index: 70