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

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

Neuron 5175 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: 3.2521. Min Range: -3.2521

Max Act: 3.2521. Min Act: -0.0000

Data Index: 898699 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.9842. Min Act: -0.0000

Data Index: 1355830 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.9429. Min Act: -0.0000

Data Index: 269976 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.9375. Min Act: -0.0000

Data Index: 1254660 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.7517. Min Act: -0.0000

Data Index: 273102 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.8390. Min Act: -0.0000

Data Index: 123835 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.6710. Min Act: -0.0000

Data Index: 843594 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.4947. Min Act: -0.0000

Data Index: 862552 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.6260. Min Act: -0.0000

Data Index: 91307 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.6215. Min Act: -0.0000

Data Index: 7639 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.5991. Min Act: -0.0000

Data Index: 76747 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.5769. Min Act: -0.0000

Data Index: 860325 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.5047. Min Act: -0.0000

Data Index: 587234 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.4879. Min Act: -0.0000

Data Index: 65416 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.4804. Min Act: -0.0000

Data Index: 331979 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.4775. Min Act: -0.0000

Data Index: 401732 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.4487. Min Act: -0.0000

Data Index: 208710 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.4490. Min Act: -0.0000

Data Index: 229094 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.4336. Min Act: -0.0000

Data Index: 542978 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 3.2521. Min Range: -3.2521

Max Act: 2.3303. Min Act: -0.0000

Data Index: 34480 (C4 (Web Text))

Max Activating Token Index: 970