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

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

Neuron 563 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.4108. Min Act: -0.0000

Data Index: 1275489 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 3.4108. Min Range: -3.4108

Max Act: 2.8765. Min Act: 0.0000

Data Index: 741737 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.7020. Min Act: -0.0000

Data Index: 396039 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.8625. Min Act: -0.0000

Data Index: 1221652 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.8421. Min Act: -0.0000

Data Index: 166510 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.5600. Min Act: -0.0000

Data Index: 373838 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.3750. Min Act: -0.0000

Data Index: 72544 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.4728. Min Act: -0.0000

Data Index: 645107 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.2541. Min Act: -0.0000

Data Index: 64363 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.2388. Min Act: -0.0000

Data Index: 1172472 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.2561. Min Act: -0.0000

Data Index: 564973 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.1409. Min Act: -0.0000

Data Index: 902480 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.1758. Min Act: -0.0000

Data Index: 1488745 (Python Code)

Max Activating Token Index: 620

Text #13

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.0503. Min Act: -0.0000

Data Index: 1102354 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1588777 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1455043 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1331683 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1397604 (Python Code)

Max Activating Token Index: 232

Text #18

Max Range: 3.4108. Min Range: -3.4108

Max Act: 1.0746. Min Act: -0.0000

Data Index: 930458 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 3.4108. Min Range: -3.4108

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1543719 (Python Code)

Max Activating Token Index: 933