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

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

Neuron 559 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: 0.5940. Min Range: -0.5940

Max Act: 0.5940. Min Act: -0.0000

Data Index: 12709 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1079388 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1309310 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4957. Min Act: -0.0000

Data Index: 304456 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4766. Min Act: -0.0000

Data Index: 752367 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4122. Min Act: -0.0000

Data Index: 838643 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1118213 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1115645 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1088836 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3577. Min Act: -0.0000

Data Index: 153752 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3667. Min Act: -0.0000

Data Index: 448440 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3909. Min Act: -0.0000

Data Index: 466648 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3767. Min Act: -0.0000

Data Index: 869342 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3563. Min Act: -0.0000

Data Index: 493090 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3514. Min Act: -0.0000

Data Index: 859898 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3336. Min Act: -0.0000

Data Index: 641473 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1243152 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3466. Min Act: -0.0000

Data Index: 600466 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3335. Min Act: -0.0000

Data Index: 370131 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3385. Min Act: -0.0000

Data Index: 812082 (C4 (Web Text))

Max Activating Token Index: 848