Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3634 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0620. Min Act: -0.0002

Data Index: 771777 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1186885 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0535. Min Act: -0.0002

Data Index: 503755 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0535. Min Act: -0.0002

Data Index: 411904 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1335570 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0539. Min Act: -0.0002

Data Index: 184119 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0489. Min Act: -0.0002

Data Index: 235072 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1142843 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0475. Min Act: -0.0002

Data Index: 443998 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1126012 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0495. Min Act: -0.0002

Data Index: 600661 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0530. Min Act: -0.0002

Data Index: 66528 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0500. Min Act: -0.0002

Data Index: 434341 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0434. Min Act: -0.0002

Data Index: 905693 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0466. Min Act: -0.0002

Data Index: 134285 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0506. Min Act: -0.0002

Data Index: 935020 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1100814 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0459. Min Act: -0.0002

Data Index: 484152 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0441. Min Act: -0.0002

Data Index: 543692 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0454. Min Act: -0.0002

Data Index: 501565 (C4 (Web Text))

Max Activating Token Index: 14