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

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

Neuron 3513 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1767. Min Range: -3.1767

Max Act: 3.1767. Min Act: -0.0001

Data Index: 619539 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.7961. Min Act: -0.0001

Data Index: 1023178 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.5672. Min Act: -0.0001

Data Index: 125488 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.6576. Min Act: -0.0001

Data Index: 645874 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.3813. Min Act: -0.0001

Data Index: 488365 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.4753. Min Act: -0.0001

Data Index: 362145 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.3771. Min Act: -0.0001

Data Index: 717264 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.3385. Min Act: -0.0001

Data Index: 804211 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.4147. Min Act: -0.0001

Data Index: 809528 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.4221. Min Act: -0.0001

Data Index: 1302006 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.2983. Min Act: -0.0001

Data Index: 182616 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.2440. Min Act: -0.0001

Data Index: 994242 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.3555. Min Act: -0.0001

Data Index: 1192536 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.2387. Min Act: -0.0001

Data Index: 777401 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.1147. Min Act: -0.0001

Data Index: 736424 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.2053. Min Act: -0.0001

Data Index: 528590 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.1726. Min Act: -0.0001

Data Index: 37201 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.1514. Min Act: -0.0001

Data Index: 877747 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.1604. Min Act: -0.0001

Data Index: 652726 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 3.1767. Min Range: -3.1767

Max Act: 2.1155. Min Act: -0.0001

Data Index: 843699 (C4 (Web Text))

Max Activating Token Index: 713