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

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

Neuron 773 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: 1.1620. Min Range: -1.1620

Max Act: 1.1620. Min Act: -0.0000

Data Index: 1033478 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9658. Min Act: -0.0000

Data Index: 537467 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.0128. Min Act: -0.0000

Data Index: 898558 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9432. Min Act: -0.0000

Data Index: 405945 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1131008 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.8969. Min Act: -0.0000

Data Index: 1021954 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9466. Min Act: -0.0000

Data Index: 213707 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9474. Min Act: -0.0000

Data Index: 851416 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9394. Min Act: -0.0000

Data Index: 200081 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.8980. Min Act: -0.0000

Data Index: 986521 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.8930. Min Act: -0.0000

Data Index: 809597 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1399456 (Python Code)

Max Activating Token Index: 1017

Text #12

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.7707. Min Act: -0.0000

Data Index: 332767 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.8143. Min Act: -0.0000

Data Index: 643805 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.8421. Min Act: -0.0000

Data Index: 472125 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.8309. Min Act: -0.0000

Data Index: 548068 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.8012. Min Act: -0.0000

Data Index: 891543 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1318626 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.8769. Min Act: -0.0000

Data Index: 442177 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.7892. Min Act: -0.0000

Data Index: 834017 (C4 (Web Text))

Max Activating Token Index: 407