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

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

Neuron 4329 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: 5.1956. Min Range: -5.1956

Max Act: 5.1956. Min Act: -0.0000

Data Index: 852683 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.1760. Min Act: -0.0000

Data Index: 988852 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.3355. Min Act: -0.0000

Data Index: 659535 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.5195. Min Act: -0.0000

Data Index: 1015108 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.0295. Min Act: -0.0000

Data Index: 1035856 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 5.1956. Min Range: -5.1956

Max Act: 3.8651. Min Act: -0.0000

Data Index: 326912 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 5.1956. Min Range: -5.1956

Max Act: 3.5925. Min Act: -0.0000

Data Index: 1250422 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 5.1956. Min Range: -5.1956

Max Act: 3.3333. Min Act: -0.0000

Data Index: 1540209 (Python Code)

Max Activating Token Index: 518

Text #8

Max Range: 5.1956. Min Range: -5.1956

Max Act: 2.8452. Min Act: -0.0000

Data Index: 1436426 (Python Code)

Max Activating Token Index: 367

Text #9

Max Range: 5.1956. Min Range: -5.1956

Max Act: 2.6107. Min Act: -0.0000

Data Index: 1053673 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 5.1956. Min Range: -5.1956

Max Act: 2.7323. Min Act: -0.0000

Data Index: 1150286 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 5.1956. Min Range: -5.1956

Max Act: 2.9806. Min Act: -0.0000

Data Index: 95628 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 5.1956. Min Range: -5.1956

Max Act: 2.6452. Min Act: -0.0000

Data Index: 647910 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 5.1956. Min Range: -5.1956

Max Act: 2.7634. Min Act: -0.0000

Data Index: 1343775 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 5.1956. Min Range: -5.1956

Max Act: 2.2931. Min Act: -0.0000

Data Index: 792753 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 5.1956. Min Range: -5.1956

Max Act: 2.5133. Min Act: -0.0000

Data Index: 911208 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 5.1956. Min Range: -5.1956

Max Act: 2.4895. Min Act: -0.0000

Data Index: 1365475 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 5.1956. Min Range: -5.1956

Max Act: 2.4342. Min Act: -0.0000

Data Index: 1421539 (Python Code)

Max Activating Token Index: 955

Text #18

Max Range: 5.1956. Min Range: -5.1956

Max Act: 2.4239. Min Act: -0.0000

Data Index: 314603 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 5.1956. Min Range: -5.1956

Max Act: 2.5425. Min Act: -0.0000

Data Index: 1458835 (Python Code)

Max Activating Token Index: 931