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

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

Neuron 5595 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: 539025 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0611. Min Act: -0.0002

Data Index: 732009 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0610. Min Act: -0.0002

Data Index: 23883 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1115566 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0548. Min Act: -0.0002

Data Index: 697004 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1102934 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0540. Min Act: -0.0002

Data Index: 307316 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0531. Min Act: -0.0002

Data Index: 521531 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0509. Min Act: -0.0002

Data Index: 509118 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0509. Min Act: -0.0002

Data Index: 288428 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1028231 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0495. Min Act: -0.0002

Data Index: 493183 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0489. Min Act: -0.0002

Data Index: 699950 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0490. Min Act: -0.0002

Data Index: 371462 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0478. Min Act: -0.0002

Data Index: 742658 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0482. Min Act: -0.0002

Data Index: 634450 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0475. Min Act: -0.0002

Data Index: 537161 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0473. Min Act: -0.0002

Data Index: 75590 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0471. Min Act: -0.0002

Data Index: 144851 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1266332 (C4 (Web Text))

Max Activating Token Index: 602