Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 970 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0639. Min Act: -0.0006

Data Index: 345611 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0540. Min Act: -0.0006

Data Index: 86542 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0602. Min Act: -0.0006

Data Index: 272348 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0538. Min Act: -0.0006

Data Index: 1324586 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0478. Min Act: -0.0006

Data Index: 202299 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0581. Min Act: -0.0006

Data Index: 809946 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0527. Min Act: -0.0006

Data Index: 26459 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0524. Min Act: -0.0006

Data Index: 727177 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0529. Min Act: -0.0006

Data Index: 505595 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0501. Min Act: -0.0006

Data Index: 1036034 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0522. Min Act: -0.0006

Data Index: 1223925 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0481. Min Act: -0.0006

Data Index: 840593 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0439. Min Act: -0.0006

Data Index: 803757 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0490. Min Act: -0.0006

Data Index: 565535 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0550. Min Act: -0.0006

Data Index: 670762 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0413. Min Act: -0.0006

Data Index: 754926 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0476. Min Act: -0.0006

Data Index: 160031 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0461. Min Act: -0.0006

Data Index: 1108632 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0533. Min Act: -0.0006

Data Index: 184593 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0487. Min Act: -0.0006

Data Index: 1342207 (C4 (Web Text))

Max Activating Token Index: 414