Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2266 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.8630. Min Act: -0.0000

Data Index: 298071 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.7368. Min Act: -0.0000

Data Index: 1472921 (Python Code)

Max Activating Token Index: 801

Text #2

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.6065. Min Act: -0.0000

Data Index: 1618950 (Python Code)

Max Activating Token Index: 741

Text #3

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.5633. Min Act: -0.0000

Data Index: 526207 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.5490. Min Act: -0.0000

Data Index: 1362638 (Python Code)

Max Activating Token Index: 844

Text #5

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.4516. Min Act: -0.0000

Data Index: 1644683 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.4980. Min Act: -0.0000

Data Index: 733201 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.4051. Min Act: -0.0000

Data Index: 180262 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.5187. Min Act: -0.0000

Data Index: 1625945 (Python Code)

Max Activating Token Index: 410

Text #9

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.4769. Min Act: -0.0000

Data Index: 1050278 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.4579. Min Act: -0.0000

Data Index: 734267 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.4591. Min Act: -0.0000

Data Index: 1330582 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.4469. Min Act: -0.0000

Data Index: 1468043 (Python Code)

Max Activating Token Index: 818

Text #13

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.4563. Min Act: -0.0000

Data Index: 1441454 (Python Code)

Max Activating Token Index: 845

Text #14

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.3967. Min Act: -0.0000

Data Index: 11767 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.3953. Min Act: -0.0000

Data Index: 555014 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.4539. Min Act: -0.0000

Data Index: 1157302 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.3644. Min Act: -0.0000

Data Index: 1045741 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.4383. Min Act: -0.0000

Data Index: 1422529 (Python Code)

Max Activating Token Index: 783

Text #19

Max Range: 1.8630. Min Range: -1.8630

Max Act: 1.2751. Min Act: -0.0000

Data Index: 465399 (C4 (Web Text))

Max Activating Token Index: 285