Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 547 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4047. Min Act: -0.0001

Data Index: 109116 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4435. Min Act: -0.0001

Data Index: 610174 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3897. Min Act: -0.0001

Data Index: 183064 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3659. Min Act: -0.0001

Data Index: 1031964 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4046. Min Act: -0.0001

Data Index: 284751 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3841. Min Act: -0.0001

Data Index: 697296 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3592. Min Act: -0.0001

Data Index: 405280 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3791. Min Act: -0.0001

Data Index: 749544 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3666. Min Act: -0.0001

Data Index: 747682 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3639. Min Act: -0.0001

Data Index: 340082 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3650. Min Act: -0.0001

Data Index: 1149086 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3623. Min Act: -0.0001

Data Index: 1114876 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3694. Min Act: -0.0001

Data Index: 2934 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3589. Min Act: -0.0001

Data Index: 369121 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3826. Min Act: -0.0001

Data Index: 1204364 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3683. Min Act: -0.0001

Data Index: 884681 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3515. Min Act: -0.0001

Data Index: 662611 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3644. Min Act: -0.0001

Data Index: 273776 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3657. Min Act: -0.0001

Data Index: 461231 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3411. Min Act: -0.0001

Data Index: 338769 (C4 (Web Text))

Max Activating Token Index: 743