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

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

Neuron 3313 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.5031. Min Act: -0.0000

Data Index: 286381 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4522. Min Act: -0.0000

Data Index: 773543 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4946. Min Act: -0.0000

Data Index: 849368 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.5040. Min Act: -0.0000

Data Index: 102481 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1233859 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1045043 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4815. Min Act: -0.0000

Data Index: 426637 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4634. Min Act: -0.0000

Data Index: 466346 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4758. Min Act: -0.0000

Data Index: 930338 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4582. Min Act: -0.0000

Data Index: 935980 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4782. Min Act: -0.0000

Data Index: 944083 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4583. Min Act: -0.0000

Data Index: 635799 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.5039. Min Act: -0.0000

Data Index: 473417 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4836. Min Act: -0.0000

Data Index: 81648 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4626. Min Act: -0.0000

Data Index: 980099 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4614. Min Act: -0.0000

Data Index: 97641 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4276. Min Act: -0.0000

Data Index: 951294 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4114. Min Act: -0.0000

Data Index: 997845 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1009578 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4523. Min Act: -0.0000

Data Index: 995604 (C4 (Web Text))

Max Activating Token Index: 241