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

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

Neuron 3168 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: 0.5516. Min Range: -0.5516

Max Act: 0.5338. Min Act: -0.0001

Data Index: 833085 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.5516. Min Act: -0.0001

Data Index: 736756 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4607. Min Act: -0.0001

Data Index: 683523 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4781. Min Act: -0.0001

Data Index: 145365 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4761. Min Act: -0.0001

Data Index: 802412 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4644. Min Act: -0.0001

Data Index: 206238 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4553. Min Act: -0.0001

Data Index: 120629 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4726. Min Act: -0.0001

Data Index: 426754 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4916. Min Act: -0.0001

Data Index: 954036 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4346. Min Act: -0.0001

Data Index: 1126324 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4719. Min Act: -0.0001

Data Index: 1152840 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4712. Min Act: -0.0001

Data Index: 196077 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4535. Min Act: -0.0001

Data Index: 960704 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4386. Min Act: -0.0001

Data Index: 323395 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4620. Min Act: -0.0001

Data Index: 154518 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4250. Min Act: -0.0001

Data Index: 161544 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4344. Min Act: -0.0001

Data Index: 1004632 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4422. Min Act: -0.0001

Data Index: 85390 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4748. Min Act: -0.0001

Data Index: 83078 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4373. Min Act: -0.0001

Data Index: 1052750 (C4 (Web Text))

Max Activating Token Index: 656