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

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

Neuron 2493 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7884. Min Act: -0.0001

Data Index: 147521 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.8814. Min Act: -0.0001

Data Index: 317323 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.8388. Min Act: -0.0001

Data Index: 1419761 (Python Code)

Max Activating Token Index: 991

Text #3

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.8411. Min Act: -0.0001

Data Index: 207591 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7993. Min Act: -0.0001

Data Index: 20135 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7465. Min Act: -0.0001

Data Index: 888287 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7871. Min Act: -0.0001

Data Index: 1537147 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7424. Min Act: -0.0001

Data Index: 793720 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7843. Min Act: -0.0001

Data Index: 1151374 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7083. Min Act: -0.0001

Data Index: 1427055 (Python Code)

Max Activating Token Index: 596

Text #10

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7473. Min Act: -0.0001

Data Index: 460420 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7198. Min Act: -0.0001

Data Index: 992486 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.6717. Min Act: -0.0001

Data Index: 1521072 (Python Code)

Max Activating Token Index: 507

Text #13

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.6908. Min Act: -0.0001

Data Index: 1526735 (Python Code)

Max Activating Token Index: 45

Text #14

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7498. Min Act: -0.0001

Data Index: 1651778 (Python Code)

Max Activating Token Index: 892

Text #15

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7674. Min Act: -0.0001

Data Index: 1654248 (Python Code)

Max Activating Token Index: 912

Text #16

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7274. Min Act: -0.0001

Data Index: 1268016 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7036. Min Act: -0.0001

Data Index: 475955 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.6983. Min Act: -0.0001

Data Index: 885314 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.6705. Min Act: -0.0001

Data Index: 278401 (C4 (Web Text))

Max Activating Token Index: 595