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

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

Neuron 1643 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.7698. Min Act: -0.0000

Data Index: 235594 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6771. Min Act: -0.0000

Data Index: 923422 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6431. Min Act: -0.0000

Data Index: 857105 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6232. Min Act: -0.0000

Data Index: 456452 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.5825. Min Act: -0.0000

Data Index: 257982 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1286464 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1159509 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4993. Min Act: 0.0000

Data Index: 1306326 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4754. Min Act: -0.0000

Data Index: 692990 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4729. Min Act: -0.0000

Data Index: 767030 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4980. Min Act: -0.0000

Data Index: 714006 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4684. Min Act: 0.0000

Data Index: 1154455 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4653. Min Act: -0.0000

Data Index: 86132 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4622. Min Act: -0.0000

Data Index: 29367 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4520. Min Act: -0.0000

Data Index: 178676 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4459. Min Act: -0.0000

Data Index: 622128 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4418. Min Act: -0.0000

Data Index: 430977 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4099. Min Act: 0.0000

Data Index: 602787 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1319407 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.4319. Min Act: -0.0000

Data Index: 85897 (C4 (Web Text))

Max Activating Token Index: 776