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

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

Neuron 832 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.3263. Min Act: -0.0001

Data Index: 106470 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1631775 (Python Code)

Max Activating Token Index: 342

Text #2

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.3641. Min Act: -0.0000

Data Index: 749495 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1240243 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2705. Min Act: -0.0000

Data Index: 218182 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2984. Min Act: -0.0000

Data Index: 192751 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2620. Min Act: -0.0000

Data Index: 570451 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1104804 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2703. Min Act: -0.0001

Data Index: 844288 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2505. Min Act: -0.0000

Data Index: 725030 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2201. Min Act: -0.0000

Data Index: 887117 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2096. Min Act: -0.0001

Data Index: 927316 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2068. Min Act: -0.0000

Data Index: 547986 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1546332 (Python Code)

Max Activating Token Index: 1020

Text #14

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.1910. Min Act: -0.0000

Data Index: 473405 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2139. Min Act: -0.0000

Data Index: 281402 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.1968. Min Act: -0.0001

Data Index: 877889 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1583065 (Python Code)

Max Activating Token Index: 657

Text #18

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.1799. Min Act: -0.0000

Data Index: 821562 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1524759 (Python Code)

Max Activating Token Index: 503