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

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

Neuron 561 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0698. Min Act: -0.0001

Data Index: 111582 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0627. Min Act: -0.0001

Data Index: 770011 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1084082 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1603395 (Python Code)

Max Activating Token Index: 20

Text #4

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1475025 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0422. Min Act: -0.0001

Data Index: 1637393 (Python Code)

Max Activating Token Index: 21

Text #6

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0358. Min Act: -0.0001

Data Index: 508754 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0411. Min Act: -0.0001

Data Index: 772417 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0374. Min Act: -0.0001

Data Index: 280744 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0348. Min Act: -0.0001

Data Index: 1285762 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0357. Min Act: -0.0002

Data Index: 450040 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0363. Min Act: -0.0001

Data Index: 806762 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0328. Min Act: -0.0001

Data Index: 30789 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0374. Min Act: -0.0001

Data Index: 329569 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0358. Min Act: -0.0001

Data Index: 198095 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1099040 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0342. Min Act: -0.0001

Data Index: 292497 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0245. Min Act: -0.0001

Data Index: 249748 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0336. Min Act: -0.0001

Data Index: 292696 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0358. Min Act: -0.0001

Data Index: 151819 (C4 (Web Text))

Max Activating Token Index: 83