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

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

Neuron 2746 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2841. Min Range: -1.2841

Max Act: 1.2841. Min Act: -0.0000

Data Index: 1298174 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 1.2841. Min Range: -1.2841

Max Act: 1.1476. Min Act: -0.0000

Data Index: 1011561 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 1.2841. Min Range: -1.2841

Max Act: 1.1318. Min Act: -0.0000

Data Index: 554278 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9528. Min Act: -0.0000

Data Index: 188141 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9645. Min Act: -0.0000

Data Index: 14076 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9426. Min Act: -0.0000

Data Index: 323562 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1224596 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1039469 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9134. Min Act: -0.0000

Data Index: 549277 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1357721 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9116. Min Act: -0.0000

Data Index: 860194 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8538. Min Act: -0.0000

Data Index: 973616 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8634. Min Act: -0.0000

Data Index: 386999 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8907. Min Act: -0.0000

Data Index: 927864 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8897. Min Act: -0.0000

Data Index: 97429 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8851. Min Act: -0.0000

Data Index: 340686 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8531. Min Act: -0.0000

Data Index: 721565 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1036623 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8390. Min Act: -0.0000

Data Index: 538266 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8290. Min Act: -0.0000

Data Index: 905335 (C4 (Web Text))

Max Activating Token Index: 173