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

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

Neuron 5583 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: 0.7540. Min Range: -0.7540

Max Act: 0.7540. Min Act: -0.0000

Data Index: 635875 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5628. Min Act: -0.0000

Data Index: 131902 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5287. Min Act: -0.0000

Data Index: 982753 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4493. Min Act: -0.0000

Data Index: 916823 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5120. Min Act: -0.0000

Data Index: 752422 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1187715 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4218. Min Act: -0.0000

Data Index: 696081 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4716. Min Act: -0.0000

Data Index: 470482 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4331. Min Act: -0.0000

Data Index: 512850 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1161107 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4466. Min Act: -0.0000

Data Index: 194039 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4219. Min Act: -0.0000

Data Index: 325128 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4341. Min Act: -0.0000

Data Index: 191406 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1384977 (Python Code)

Max Activating Token Index: 857

Text #14

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4436. Min Act: -0.0000

Data Index: 82324 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4183. Min Act: -0.0000

Data Index: 682429 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.3679. Min Act: -0.0000

Data Index: 375840 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4156. Min Act: -0.0000

Data Index: 799794 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1622898 (Python Code)

Max Activating Token Index: 821

Text #19

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4334. Min Act: -0.0000

Data Index: 362274 (C4 (Web Text))

Max Activating Token Index: 823