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

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

Neuron 6084 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.6797. Min Act: -0.0000

Data Index: 695086 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.6122. Min Act: -0.0000

Data Index: 671117 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1052962 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5577. Min Act: -0.0000

Data Index: 276662 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1176445 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1218964 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5030. Min Act: -0.0000

Data Index: 888915 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5142. Min Act: -0.0000

Data Index: 884454 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.4974. Min Act: -0.0000

Data Index: 192828 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1339180 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.4855. Min Act: -0.0000

Data Index: 961391 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.4517. Min Act: -0.0000

Data Index: 424923 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.4653. Min Act: -0.0000

Data Index: 489580 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1337687 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1066968 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.4791. Min Act: -0.0000

Data Index: 173526 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.4830. Min Act: -0.0000

Data Index: 375377 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.4562. Min Act: -0.0000

Data Index: 791467 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.4831. Min Act: -0.0000

Data Index: 718648 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.4470. Min Act: -0.0000

Data Index: 443616 (C4 (Web Text))

Max Activating Token Index: 35