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

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

Neuron 3933 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: 0.8349. Min Range: -0.8349

Max Act: 0.8349. Min Act: 0.0001

Data Index: 472123 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.7798. Min Act: 0.0001

Data Index: 1006282 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.7571. Min Act: 0.0001

Data Index: 1143430 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.7363. Min Act: 0.0001

Data Index: 1122973 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1566951 (Python Code)

Max Activating Token Index: 892

Text #5

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6792. Min Act: -0.0000

Data Index: 187052 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6929. Min Act: -0.0000

Data Index: 283052 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1414364 (Python Code)

Max Activating Token Index: 596

Text #8

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1345135 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6476. Min Act: -0.0000

Data Index: 653622 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6935. Min Act: 0.0001

Data Index: 667889 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6483. Min Act: -0.0000

Data Index: 166457 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6214. Min Act: 0.0000

Data Index: 1333422 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6476. Min Act: 0.0000

Data Index: 1557106 (Python Code)

Max Activating Token Index: 543

Text #14

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1220915 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6266. Min Act: -0.0000

Data Index: 291764 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6276. Min Act: 0.0001

Data Index: 705401 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1291473 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6333. Min Act: 0.0001

Data Index: 712026 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.5875. Min Act: -0.0000

Data Index: 841616 (C4 (Web Text))

Max Activating Token Index: 416