Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3678 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1213098 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0562. Min Act: -0.0002

Data Index: 956810 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1091973 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1130248 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1097322 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0514. Min Act: -0.0002

Data Index: 352853 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1081179 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0506. Min Act: -0.0002

Data Index: 606651 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1294305 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0485. Min Act: -0.0002

Data Index: 559915 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1103569 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0465. Min Act: -0.0002

Data Index: 249510 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0466. Min Act: -0.0002

Data Index: 304755 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0437. Min Act: -0.0002

Data Index: 133509 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0446. Min Act: -0.0002

Data Index: 731001 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0430. Min Act: -0.0002

Data Index: 618790 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0445. Min Act: -0.0002

Data Index: 493778 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1296395 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0415. Min Act: -0.0002

Data Index: 147930 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0406. Min Act: -0.0002

Data Index: 171354 (C4 (Web Text))

Max Activating Token Index: 610