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

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

Neuron 2911 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9849. Min Range: -2.9849

Max Act: 2.9849. Min Act: -0.0000

Data Index: 373675 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 2.9849. Min Range: -2.9849

Max Act: 2.7071. Min Act: -0.0000

Data Index: 1288209 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 2.9849. Min Range: -2.9849

Max Act: 2.4948. Min Act: -0.0000

Data Index: 164326 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 2.9849. Min Range: -2.9849

Max Act: 2.4464. Min Act: -0.0000

Data Index: 1170980 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 2.9849. Min Range: -2.9849

Max Act: 2.5519. Min Act: -0.0000

Data Index: 416591 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 2.9849. Min Range: -2.9849

Max Act: 2.4016. Min Act: -0.0000

Data Index: 187614 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 2.9849. Min Range: -2.9849

Max Act: 2.1502. Min Act: -0.0000

Data Index: 495578 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 2.9849. Min Range: -2.9849

Max Act: 2.0932. Min Act: -0.0000

Data Index: 906949 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 2.9849. Min Range: -2.9849

Max Act: 1.9771. Min Act: -0.0000

Data Index: 645316 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 2.9849. Min Range: -2.9849

Max Act: 2.0540. Min Act: -0.0000

Data Index: 693766 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 2.9849. Min Range: -2.9849

Max Act: 2.0349. Min Act: -0.0000

Data Index: 1336893 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 2.9849. Min Range: -2.9849

Max Act: 2.0049. Min Act: -0.0000

Data Index: 190743 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 2.9849. Min Range: -2.9849

Max Act: 1.9828. Min Act: -0.0000

Data Index: 795747 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 2.9849. Min Range: -2.9849

Max Act: 1.9357. Min Act: -0.0000

Data Index: 1202548 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 2.9849. Min Range: -2.9849

Max Act: 2.0435. Min Act: -0.0000

Data Index: 380990 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 2.9849. Min Range: -2.9849

Max Act: 1.9180. Min Act: -0.0000

Data Index: 1102394 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 2.9849. Min Range: -2.9849

Max Act: 1.8852. Min Act: -0.0000

Data Index: 128635 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 2.9849. Min Range: -2.9849

Max Act: 1.8636. Min Act: -0.0000

Data Index: 546792 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 2.9849. Min Range: -2.9849

Max Act: 1.8538. Min Act: -0.0000

Data Index: 1320485 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 2.9849. Min Range: -2.9849

Max Act: 1.8204. Min Act: -0.0000

Data Index: 820588 (C4 (Web Text))

Max Activating Token Index: 110