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

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

Neuron 2756 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0611. Min Range: -4.0611

Max Act: 4.0611. Min Act: -0.0001

Data Index: 1002422 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 4.0611. Min Range: -4.0611

Max Act: 3.9007. Min Act: -0.0000

Data Index: 709550 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 4.0611. Min Range: -4.0611

Max Act: 3.3909. Min Act: -0.0001

Data Index: 1174312 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 4.0611. Min Range: -4.0611

Max Act: 3.1738. Min Act: -0.0001

Data Index: 1069264 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.7136. Min Act: -0.0001

Data Index: 466804 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 4.0611. Min Range: -4.0611

Max Act: 3.1469. Min Act: -0.0001

Data Index: 496334 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.7861. Min Act: -0.0001

Data Index: 1286292 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.7979. Min Act: -0.0000

Data Index: 744066 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.8582. Min Act: -0.0001

Data Index: 107357 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 4.0611. Min Range: -4.0611

Max Act: 3.0014. Min Act: -0.0000

Data Index: 80558 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.7242. Min Act: -0.0001

Data Index: 749196 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 4.0611. Min Range: -4.0611

Max Act: 3.1276. Min Act: -0.0000

Data Index: 715810 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.6949. Min Act: -0.0001

Data Index: 440118 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.5738. Min Act: -0.0000

Data Index: 528794 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.8326. Min Act: -0.0001

Data Index: 843152 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.8024. Min Act: -0.0001

Data Index: 607773 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.9037. Min Act: -0.0001

Data Index: 625158 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.4775. Min Act: -0.0001

Data Index: 30136 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.5328. Min Act: -0.0001

Data Index: 965856 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 4.0611. Min Range: -4.0611

Max Act: 2.3911. Min Act: -0.0001

Data Index: 903489 (C4 (Web Text))

Max Activating Token Index: 1016