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

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

Neuron 2089 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: 0.1958. Min Range: -0.1958

Max Act: 0.1958. Min Act: -0.0003

Data Index: 463339 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1806. Min Act: -0.0003

Data Index: 719938 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1733. Min Act: -0.0003

Data Index: 1137797 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1712. Min Act: -0.0003

Data Index: 233248 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1851. Min Act: -0.0003

Data Index: 1209755 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1736. Min Act: -0.0003

Data Index: 802919 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1705. Min Act: -0.0003

Data Index: 1319576 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1698. Min Act: -0.0003

Data Index: 666210 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1627. Min Act: -0.0003

Data Index: 1046859 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1711. Min Act: -0.0003

Data Index: 358194 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1632. Min Act: -0.0003

Data Index: 919130 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1552. Min Act: -0.0003

Data Index: 383377 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1684. Min Act: -0.0003

Data Index: 803272 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1637. Min Act: -0.0003

Data Index: 159556 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1544. Min Act: -0.0003

Data Index: 338125 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1631. Min Act: -0.0003

Data Index: 983713 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1525. Min Act: -0.0003

Data Index: 510381 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1291. Min Act: -0.0003

Data Index: 1044698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1556. Min Act: -0.0003

Data Index: 171975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1454. Min Act: -0.0003

Data Index: 130856 (C4 (Web Text))

Max Activating Token Index: 1023