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

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

Neuron 4438 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.6084. Min Act: -0.0000

Data Index: 520451 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4442. Min Act: -0.0000

Data Index: 400345 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.5269. Min Act: -0.0000

Data Index: 490930 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.5434. Min Act: -0.0000

Data Index: 730498 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.3256. Min Act: -0.0000

Data Index: 976449 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4534. Min Act: -0.0000

Data Index: 201205 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.3636. Min Act: -0.0000

Data Index: 95798 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.3524. Min Act: -0.0000

Data Index: 848426 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.2506. Min Act: -0.0000

Data Index: 1260512 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.2588. Min Act: -0.0000

Data Index: 1076967 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.1010. Min Act: -0.0000

Data Index: 160879 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.1126. Min Act: -0.0000

Data Index: 455865 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1414480 (Python Code)

Max Activating Token Index: 174

Text #13

Max Range: 1.6084. Min Range: -1.6084

Max Act: 0.8810. Min Act: -0.0000

Data Index: 185383 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 1.6084. Min Range: -1.6084

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1347164 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.0331. Min Act: -0.0000

Data Index: 33181 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 1.6084. Min Range: -1.6084

Max Act: 0.8593. Min Act: -0.0000

Data Index: 177748 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 1.6084. Min Range: -1.6084

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1490462 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 1.6084. Min Range: -1.6084

Max Act: 0.8956. Min Act: -0.0000

Data Index: 306684 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 1.6084. Min Range: -1.6084

Max Act: 0.8497. Min Act: -0.0000

Data Index: 151782 (C4 (Web Text))

Max Activating Token Index: 963