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

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

Neuron 4060 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3790. Min Act: -0.0000

Data Index: 82699 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3840. Min Act: -0.0000

Data Index: 320909 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.4336. Min Act: -0.0000

Data Index: 287218 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3813. Min Act: -0.0000

Data Index: 701488 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.4189. Min Act: -0.0000

Data Index: 560470 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1301155 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1312786 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1309395 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1074254 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3479. Min Act: -0.0000

Data Index: 239130 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3348. Min Act: -0.0000

Data Index: 232744 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3309. Min Act: -0.0000

Data Index: 783656 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1162826 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3496. Min Act: -0.0000

Data Index: 524580 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.2935. Min Act: -0.0000

Data Index: 616102 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.2505. Min Act: -0.0000

Data Index: 429946 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1319102 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3083. Min Act: -0.0000

Data Index: 953996 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3190. Min Act: -0.0000

Data Index: 682920 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.2885. Min Act: -0.0000

Data Index: 985558 (C4 (Web Text))

Max Activating Token Index: 600