Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 391 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0558. Min Act: -0.0003

Data Index: 356593 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0482. Min Act: -0.0003

Data Index: 498692 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0476. Min Act: -0.0003

Data Index: 944528 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1091816 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0457. Min Act: -0.0003

Data Index: 978451 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0450. Min Act: -0.0003

Data Index: 214338 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1082641 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0400. Min Act: -0.0003

Data Index: 884671 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0408. Min Act: -0.0003

Data Index: 327733 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1322091 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0396. Min Act: -0.0003

Data Index: 121063 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0389. Min Act: -0.0003

Data Index: 582858 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1252435 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0416. Min Act: -0.0003

Data Index: 741221 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0368. Min Act: -0.0003

Data Index: 958731 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1117502 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0396. Min Act: -0.0003

Data Index: 741152 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1333317 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1182520 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1233221 (C4 (Web Text))

Max Activating Token Index: 299