Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 838 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.2108. Min Act: -0.0003

Data Index: 1114854 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1783. Min Act: -0.0003

Data Index: 1193211 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.2005. Min Act: -0.0003

Data Index: 1209650 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1998. Min Act: -0.0003

Data Index: 243883 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.2106. Min Act: -0.0003

Data Index: 491829 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1905. Min Act: -0.0003

Data Index: 1310558 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1802. Min Act: -0.0003

Data Index: 980514 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1820. Min Act: -0.0003

Data Index: 202373 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1744. Min Act: -0.0003

Data Index: 932731 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.2053. Min Act: -0.0003

Data Index: 1219373 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1727. Min Act: -0.0003

Data Index: 836042 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1935. Min Act: -0.0003

Data Index: 894015 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1860. Min Act: -0.0003

Data Index: 415021 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1982. Min Act: -0.0003

Data Index: 275419 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1858. Min Act: -0.0003

Data Index: 432844 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1845. Min Act: -0.0003

Data Index: 1039294 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1913. Min Act: -0.0003

Data Index: 875672 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1682. Min Act: -0.0003

Data Index: 1355449 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1844. Min Act: -0.0003

Data Index: 678759 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.2108. Min Range: -0.2108

Max Act: 0.1518. Min Act: -0.0003

Data Index: 503147 (C4 (Web Text))

Max Activating Token Index: 840