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

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

Neuron 1607 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.2412. Min Act: -0.0003

Data Index: 506013 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.1790. Min Act: -0.0003

Data Index: 472228 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.9019. Min Act: -0.0003

Data Index: 1020149 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.2928. Min Act: -0.0003

Data Index: 934991 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 3.2928. Min Range: -3.2928

Max Act: 3.0262. Min Act: -0.0003

Data Index: 676054 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.9139. Min Act: -0.0003

Data Index: 56697 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.8942. Min Act: -0.0003

Data Index: 13555 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.8919. Min Act: -0.0003

Data Index: 68301 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.8771. Min Act: -0.0003

Data Index: 822661 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.8712. Min Act: -0.0003

Data Index: 395516 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.7309. Min Act: -0.0003

Data Index: 1273538 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.7154. Min Act: -0.0003

Data Index: 442186 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.7007. Min Act: -0.0003

Data Index: 1254362 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.5073. Min Act: -0.0003

Data Index: 363716 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.6338. Min Act: -0.0003

Data Index: 1149536 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.5085. Min Act: -0.0003

Data Index: 147351 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.5060. Min Act: -0.0003

Data Index: 933249 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.8792. Min Act: -0.0003

Data Index: 897918 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.6974. Min Act: -0.0003

Data Index: 812115 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 3.2928. Min Range: -3.2928

Max Act: 2.5706. Min Act: -0.0003

Data Index: 1149487 (C4 (Web Text))

Max Activating Token Index: 197