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

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

Neuron 2687 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2757. Min Range: -2.2757

Max Act: 2.2552. Min Act: -0.0000

Data Index: 273865 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 2.2757. Min Range: -2.2757

Max Act: 2.1769. Min Act: -0.0000

Data Index: 1556754 (Python Code)

Max Activating Token Index: 364

Text #2

Max Range: 2.2757. Min Range: -2.2757

Max Act: 2.0606. Min Act: -0.0000

Data Index: 324029 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 2.2757. Min Range: -2.2757

Max Act: 2.1704. Min Act: -0.0000

Data Index: 1067445 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 2.2757. Min Range: -2.2757

Max Act: 2.2757. Min Act: -0.0000

Data Index: 901300 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 2.2757. Min Range: -2.2757

Max Act: 2.1414. Min Act: -0.0000

Data Index: 12145 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 2.2757. Min Range: -2.2757

Max Act: 1.9994. Min Act: -0.0000

Data Index: 599367 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 2.2757. Min Range: -2.2757

Max Act: 1.9843. Min Act: -0.0000

Data Index: 896235 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 2.2757. Min Range: -2.2757

Max Act: 2.0753. Min Act: -0.0000

Data Index: 1293400 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 2.2757. Min Range: -2.2757

Max Act: 2.0627. Min Act: -0.0000

Data Index: 1267814 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 2.2757. Min Range: -2.2757

Max Act: 2.0538. Min Act: -0.0000

Data Index: 4799 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 2.2757. Min Range: -2.2757

Max Act: 1.9079. Min Act: -0.0000

Data Index: 808914 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 2.2757. Min Range: -2.2757

Max Act: 1.9834. Min Act: -0.0000

Data Index: 474872 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 2.2757. Min Range: -2.2757

Max Act: 1.9178. Min Act: -0.0000

Data Index: 1121656 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 2.2757. Min Range: -2.2757

Max Act: 1.9297. Min Act: -0.0000

Data Index: 633922 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 2.2757. Min Range: -2.2757

Max Act: 1.9336. Min Act: -0.0000

Data Index: 446485 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 2.2757. Min Range: -2.2757

Max Act: 1.8463. Min Act: -0.0000

Data Index: 391881 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 2.2757. Min Range: -2.2757

Max Act: 1.8608. Min Act: -0.0000

Data Index: 191856 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 2.2757. Min Range: -2.2757

Max Act: 1.8457. Min Act: -0.0000

Data Index: 423908 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 2.2757. Min Range: -2.2757

Max Act: 1.7502. Min Act: -0.0000

Data Index: 1070667 (C4 (Web Text))

Max Activating Token Index: 33