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

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

Neuron 4661 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.9865. Min Act: -0.0000

Data Index: 1015341 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 1.0200. Min Range: -1.0200

Max Act: 1.0200. Min Act: -0.0000

Data Index: 138799 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.9799. Min Act: -0.0000

Data Index: 492649 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.9172. Min Act: -0.0000

Data Index: 1105558 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.8598. Min Act: 0.0000

Data Index: 151908 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1319499 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.8163. Min Act: -0.0000

Data Index: 491546 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.8469. Min Act: -0.0000

Data Index: 412572 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7916. Min Act: -0.0000

Data Index: 308031 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7929. Min Act: -0.0000

Data Index: 981820 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.8145. Min Act: -0.0000

Data Index: 919056 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1333368 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.8035. Min Act: 0.0000

Data Index: 783738 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7727. Min Act: -0.0000

Data Index: 715666 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7847. Min Act: 0.0001

Data Index: 562762 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7844. Min Act: -0.0000

Data Index: 699785 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7625. Min Act: -0.0000

Data Index: 720296 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1129991 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7913. Min Act: -0.0000

Data Index: 483156 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 1.0200. Min Range: -1.0200

Max Act: 0.7482. Min Act: 0.0000

Data Index: 388526 (C4 (Web Text))

Max Activating Token Index: 718