Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 36 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0005

Data Index: 401887 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0561. Min Act: -0.0005

Data Index: 935994 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0552. Min Act: -0.0005

Data Index: 866152 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0521. Min Act: -0.0005

Data Index: 356187 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0495. Min Act: -0.0005

Data Index: 526517 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0545. Min Act: -0.0005

Data Index: 1355158 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0569. Min Act: -0.0005

Data Index: 647226 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0510. Min Act: -0.0005

Data Index: 1228471 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0505. Min Act: -0.0005

Data Index: 561023 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0533. Min Act: -0.0005

Data Index: 667478 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0487. Min Act: -0.0005

Data Index: 663728 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0469. Min Act: -0.0005

Data Index: 446056 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0440. Min Act: -0.0005

Data Index: 60013 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0457. Min Act: -0.0005

Data Index: 736734 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0488. Min Act: -0.0005

Data Index: 49355 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0510. Min Act: -0.0005

Data Index: 1026832 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0442. Min Act: -0.0005

Data Index: 201928 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0451. Min Act: -0.0005

Data Index: 923337 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0438. Min Act: -0.0005

Data Index: 478637 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0498. Min Act: -0.0005

Data Index: 827807 (C4 (Web Text))

Max Activating Token Index: 541