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

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

Neuron 4993 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.3834. Min Act: -0.0000

Data Index: 75913 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.3483. Min Act: -0.0000

Data Index: 140739 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.3035. Min Act: -0.0000

Data Index: 577917 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.1352. Min Act: -0.0000

Data Index: 817411 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.1722. Min Act: -0.0000

Data Index: 449578 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.1599. Min Act: -0.0000

Data Index: 1259784 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.0034. Min Act: -0.0000

Data Index: 301210 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9801. Min Act: -0.0000

Data Index: 509868 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8569. Min Act: -0.0000

Data Index: 269789 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8304. Min Act: -0.0000

Data Index: 125563 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9520. Min Act: -0.0000

Data Index: 108450 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8479. Min Act: -0.0000

Data Index: 657241 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.7988. Min Act: -0.0000

Data Index: 103508 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8253. Min Act: -0.0000

Data Index: 288959 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8496. Min Act: -0.0000

Data Index: 285132 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8413. Min Act: -0.0000

Data Index: 638048 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1107390 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1172005 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8442. Min Act: -0.0000

Data Index: 178163 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8122. Min Act: -0.0000

Data Index: 246808 (C4 (Web Text))

Max Activating Token Index: 241