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

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

Neuron 1782 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.7743. Min Act: -0.0000

Data Index: 210904 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.6951. Min Act: -0.0000

Data Index: 198153 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.6707. Min Act: -0.0000

Data Index: 808551 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.6416. Min Act: -0.0000

Data Index: 380576 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.6390. Min Act: -0.0000

Data Index: 222947 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.6312. Min Act: -0.0000

Data Index: 231580 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.5855. Min Act: -0.0000

Data Index: 966995 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.6227. Min Act: -0.0000

Data Index: 103727 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.6034. Min Act: 0.0001

Data Index: 341353 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.6420. Min Act: 0.0001

Data Index: 104255 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.5991. Min Act: -0.0000

Data Index: 815430 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.6067. Min Act: 0.0000

Data Index: 361970 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.6031. Min Act: -0.0000

Data Index: 854573 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.5886. Min Act: -0.0000

Data Index: 615799 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.5687. Min Act: -0.0000

Data Index: 26553 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1317778 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.5790. Min Act: -0.0000

Data Index: 477363 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.5767. Min Act: 0.0000

Data Index: 1162639 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.5939. Min Act: -0.0000

Data Index: 561836 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.7743. Min Range: -0.7743

Max Act: 0.5903. Min Act: -0.0000

Data Index: 690387 (C4 (Web Text))

Max Activating Token Index: 639