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

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

Neuron 3793 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.2002. Min Act: -0.0001

Data Index: 167329 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.2018. Min Act: -0.0001

Data Index: 305246 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1864. Min Act: -0.0001

Data Index: 419649 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.2003. Min Act: -0.0001

Data Index: 309447 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1949. Min Act: -0.0001

Data Index: 1140982 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.2073. Min Act: -0.0001

Data Index: 47568 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1940. Min Act: -0.0001

Data Index: 793881 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1222635 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1844. Min Act: -0.0001

Data Index: 470080 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.2065. Min Act: -0.0001

Data Index: 371685 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1860. Min Act: -0.0001

Data Index: 407398 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1927. Min Act: -0.0001

Data Index: 609568 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1849. Min Act: -0.0001

Data Index: 454814 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1981. Min Act: -0.0001

Data Index: 489933 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1784. Min Act: -0.0001

Data Index: 202830 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1764. Min Act: -0.0001

Data Index: 1113336 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1831. Min Act: -0.0001

Data Index: 968970 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1627. Min Act: -0.0001

Data Index: 686526 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1827. Min Act: -0.0001

Data Index: 342040 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1671. Min Act: -0.0001

Data Index: 658958 (C4 (Web Text))

Max Activating Token Index: 1013