Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 350 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0956. Min Act: -0.0004

Data Index: 880667 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0831. Min Act: -0.0003

Data Index: 328369 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0820. Min Act: -0.0003

Data Index: 104514 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0782. Min Act: -0.0003

Data Index: 1423306 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1595416 (Python Code)

Max Activating Token Index: 859

Text #5

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0688. Min Act: -0.0003

Data Index: 1534332 (Python Code)

Max Activating Token Index: 856

Text #6

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0721. Min Act: -0.0004

Data Index: 1169554 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1642420 (Python Code)

Max Activating Token Index: 760

Text #8

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0648. Min Act: -0.0003

Data Index: 210866 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0679. Min Act: -0.0003

Data Index: 712969 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0640. Min Act: -0.0003

Data Index: 318029 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0667. Min Act: -0.0003

Data Index: 1469541 (Python Code)

Max Activating Token Index: 177

Text #12

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1457805 (Python Code)

Max Activating Token Index: 838

Text #13

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0674. Min Act: -0.0003

Data Index: 690446 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0653. Min Act: -0.0003

Data Index: 28509 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1452183 (Python Code)

Max Activating Token Index: 306

Text #16

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1538904 (Python Code)

Max Activating Token Index: 220

Text #17

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1540162 (Python Code)

Max Activating Token Index: 946

Text #18

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1533766 (Python Code)

Max Activating Token Index: 942

Text #19

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0643. Min Act: -0.0004

Data Index: 466024 (C4 (Web Text))

Max Activating Token Index: 150