Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 751 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2783. Min Act: -0.0000

Data Index: 589939 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2708. Min Act: -0.0000

Data Index: 632477 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2612. Min Act: -0.0000

Data Index: 697267 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1111963 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1104720 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2372. Min Act: -0.0000

Data Index: 474945 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2357. Min Act: -0.0000

Data Index: 93146 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1222202 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2246. Min Act: -0.0000

Data Index: 990802 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2317. Min Act: -0.0000

Data Index: 631616 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1021704 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1311954 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1312995 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1101117 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2194. Min Act: -0.0000

Data Index: 820822 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2144. Min Act: -0.0000

Data Index: 80175 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2079. Min Act: -0.0000

Data Index: 590170 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.1995. Min Act: -0.0000

Data Index: 863166 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1323444 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2161. Min Act: -0.0000

Data Index: 184447 (C4 (Web Text))

Max Activating Token Index: 618