Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3773 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6600. Min Act: -0.0001

Data Index: 1382790 (Python Code)

Max Activating Token Index: 608

Text #1

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6006. Min Act: -0.0001

Data Index: 33591 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5947. Min Act: -0.0001

Data Index: 1408456 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5969. Min Act: -0.0000

Data Index: 797699 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6050. Min Act: -0.0000

Data Index: 394905 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5838. Min Act: -0.0000

Data Index: 182428 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5637. Min Act: -0.0001

Data Index: 1609755 (Python Code)

Max Activating Token Index: 277

Text #7

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1163584 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6151. Min Act: -0.0001

Data Index: 1490063 (Python Code)

Max Activating Token Index: 560

Text #9

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1556619 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5273. Min Act: -0.0001

Data Index: 1550230 (Python Code)

Max Activating Token Index: 907

Text #11

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5232. Min Act: -0.0000

Data Index: 377752 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5388. Min Act: -0.0000

Data Index: 584997 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.4845. Min Act: -0.0001

Data Index: 954614 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5315. Min Act: -0.0000

Data Index: 927619 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5300. Min Act: -0.0000

Data Index: 123568 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.4934. Min Act: -0.0001

Data Index: 190891 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5046. Min Act: -0.0001

Data Index: 401440 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5069. Min Act: -0.0000

Data Index: 27402 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5216. Min Act: -0.0000

Data Index: 737000 (C4 (Web Text))

Max Activating Token Index: 767