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

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

Neuron 1204 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0001

Data Index: 201118 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1652848 (Python Code)

Max Activating Token Index: 584

Text #2

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0741. Min Act: -0.0001

Data Index: 811201 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0696. Min Act: -0.0001

Data Index: 593109 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1024557 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0631. Min Act: -0.0001

Data Index: 362933 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0739. Min Act: -0.0001

Data Index: 328328 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0699. Min Act: -0.0001

Data Index: 210477 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0699. Min Act: -0.0001

Data Index: 119870 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0740. Min Act: -0.0001

Data Index: 971950 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1315966 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0649. Min Act: -0.0001

Data Index: 310886 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0640. Min Act: -0.0001

Data Index: 871284 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0627. Min Act: -0.0001

Data Index: 797518 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0363. Min Act: -0.0001

Data Index: 874682 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0569. Min Act: -0.0001

Data Index: 49831 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0651. Min Act: -0.0001

Data Index: 1081438 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1226156 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0627. Min Act: -0.0001

Data Index: 157280 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1201638 (C4 (Web Text))

Max Activating Token Index: 609