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

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

Neuron 696 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: 1.7403. Min Range: -1.7403

Max Act: 1.7403. Min Act: -0.0000

Data Index: 1215927 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1289207 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.1438. Min Act: -0.0000

Data Index: 462844 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.0240. Min Act: -0.0000

Data Index: 882460 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.9543. Min Act: -0.0000

Data Index: 575546 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.8577. Min Act: -0.0000

Data Index: 727447 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.9197. Min Act: -0.0000

Data Index: 426670 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.8304. Min Act: -0.0000

Data Index: 861751 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.8326. Min Act: -0.0000

Data Index: 198548 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.8024. Min Act: -0.0000

Data Index: 433766 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1459815 (Python Code)

Max Activating Token Index: 520

Text #11

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1503514 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1399337 (Python Code)

Max Activating Token Index: 446

Text #13

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.7275. Min Act: -0.0000

Data Index: 495213 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.7356. Min Act: -0.0000

Data Index: 627239 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.7804. Min Act: -0.0000

Data Index: 61055 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.7182. Min Act: -0.0000

Data Index: 317524 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.6995. Min Act: -0.0000

Data Index: 212214 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1377603 (Python Code)

Max Activating Token Index: 782

Text #19

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.6577. Min Act: -0.0000

Data Index: 596236 (C4 (Web Text))

Max Activating Token Index: 233