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

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

Neuron 4311 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1292252 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6719. Min Act: -0.0000

Data Index: 897957 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.5326. Min Act: -0.0000

Data Index: 444722 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.5628. Min Act: -0.0000

Data Index: 250761 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.5474. Min Act: -0.0001

Data Index: 619630 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.4931. Min Act: -0.0000

Data Index: 873311 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1212700 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.4547. Min Act: -0.0001

Data Index: 765644 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.3740. Min Act: -0.0000

Data Index: 630162 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.4020. Min Act: -0.0000

Data Index: 83620 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1241369 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.4406. Min Act: -0.0000

Data Index: 447523 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.4469. Min Act: -0.0000

Data Index: 411562 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.3909. Min Act: -0.0001

Data Index: 261837 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.3918. Min Act: -0.0000

Data Index: 167001 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1270413 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.4133. Min Act: -0.0001

Data Index: 912063 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.4150. Min Act: -0.0000

Data Index: 982858 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.3862. Min Act: -0.0000

Data Index: 376765 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.4109. Min Act: -0.0000

Data Index: 21259 (C4 (Web Text))

Max Activating Token Index: 771