Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1220 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1562. Min Range: -2.1562

Max Act: 2.1562. Min Act: -0.0001

Data Index: 1044117 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.8611. Min Act: -0.0000

Data Index: 1030219 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.9002. Min Act: -0.0001

Data Index: 725056 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.7484. Min Act: -0.0001

Data Index: 1229303 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.6459. Min Act: -0.0001

Data Index: 987192 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.6092. Min Act: -0.0000

Data Index: 1170703 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.5028. Min Act: -0.0001

Data Index: 1333914 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.4551. Min Act: -0.0001

Data Index: 959098 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.5452. Min Act: -0.0000

Data Index: 312016 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.5561. Min Act: -0.0000

Data Index: 864946 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.4435. Min Act: -0.0001

Data Index: 902345 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1158175 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.4333. Min Act: -0.0001

Data Index: 493582 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.3391. Min Act: -0.0001

Data Index: 145866 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.4249. Min Act: -0.0000

Data Index: 821650 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.3575. Min Act: -0.0001

Data Index: 432670 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.3018. Min Act: -0.0000

Data Index: 780055 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.3746. Min Act: -0.0001

Data Index: 218919 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.3892. Min Act: -0.0001

Data Index: 136997 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 2.1562. Min Range: -2.1562

Max Act: 1.3061. Min Act: -0.0000

Data Index: 148541 (C4 (Web Text))

Max Activating Token Index: 234