Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1670 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0797. Min Range: -1.0797

Max Act: 1.0797. Min Act: -0.0000

Data Index: 1050309 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9807. Min Act: -0.0000

Data Index: 526033 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1171941 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9262. Min Act: -0.0000

Data Index: 599136 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 1.0797. Min Range: -1.0797

Max Act: 1.0281. Min Act: -0.0000

Data Index: 1191702 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9211. Min Act: -0.0000

Data Index: 713877 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9189. Min Act: -0.0000

Data Index: 437598 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1184589 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9240. Min Act: -0.0000

Data Index: 80372 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1272855 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8888. Min Act: -0.0000

Data Index: 432 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9125. Min Act: -0.0000

Data Index: 15307 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8710. Min Act: -0.0000

Data Index: 345040 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8619. Min Act: -0.0000

Data Index: 134025 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8237. Min Act: -0.0000

Data Index: 893725 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8838. Min Act: -0.0000

Data Index: 923805 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.7796. Min Act: -0.0000

Data Index: 502867 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8011. Min Act: -0.0000

Data Index: 872686 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.7969. Min Act: -0.0000

Data Index: 766385 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.7722. Min Act: -0.0000

Data Index: 590339 (C4 (Web Text))

Max Activating Token Index: 226