Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2932 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2312. Min Act: -0.0000

Data Index: 119631 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2093. Min Act: -0.0000

Data Index: 876419 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2173. Min Act: -0.0001

Data Index: 569283 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1309528 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1994. Min Act: -0.0000

Data Index: 403416 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2002. Min Act: -0.0000

Data Index: 607590 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1878. Min Act: -0.0001

Data Index: 270004 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1964. Min Act: -0.0000

Data Index: 813776 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1899. Min Act: -0.0001

Data Index: 1184375 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1929. Min Act: -0.0000

Data Index: 822168 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1944. Min Act: -0.0000

Data Index: 151572 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1777. Min Act: -0.0001

Data Index: 757562 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1748. Min Act: -0.0001

Data Index: 796611 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1012084 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1783. Min Act: -0.0001

Data Index: 788686 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1745. Min Act: -0.0001

Data Index: 1333896 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1139391 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1818. Min Act: -0.0001

Data Index: 472336 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1636. Min Act: -0.0001

Data Index: 491076 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1731. Min Act: -0.0001

Data Index: 277130 (C4 (Web Text))

Max Activating Token Index: 201