Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1710 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0669. Min Act: -0.0003

Data Index: 209965 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1266318 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0593. Min Act: -0.0003

Data Index: 206968 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0590. Min Act: -0.0003

Data Index: 1031470 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0595. Min Act: -0.0004

Data Index: 263336 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0590. Min Act: -0.0003

Data Index: 286667 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0561. Min Act: -0.0003

Data Index: 299397 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0559. Min Act: -0.0003

Data Index: 126131 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0543. Min Act: -0.0003

Data Index: 485086 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0538. Min Act: -0.0003

Data Index: 144822 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0527. Min Act: -0.0003

Data Index: 32645 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0538. Min Act: -0.0003

Data Index: 785722 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0550. Min Act: -0.0003

Data Index: 462431 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1290232 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0524. Min Act: -0.0003

Data Index: 987414 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0518. Min Act: -0.0003

Data Index: 381262 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0541. Min Act: -0.0004

Data Index: 204099 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1107325 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0531. Min Act: -0.0003

Data Index: 360095 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0519. Min Act: -0.0004

Data Index: 907821 (C4 (Web Text))

Max Activating Token Index: 776