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

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

Neuron 4314 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: 3.4432. Min Range: -3.4432

Max Act: 3.1430. Min Act: -0.0001

Data Index: 1108288 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 3.4432. Min Range: -3.4432

Max Act: 3.4432. Min Act: -0.0000

Data Index: 389454 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 3.4432. Min Range: -3.4432

Max Act: 3.1056. Min Act: -0.0000

Data Index: 1268542 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 3.4432. Min Range: -3.4432

Max Act: 3.2696. Min Act: -0.0000

Data Index: 966499 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 3.4432. Min Range: -3.4432

Max Act: 3.0427. Min Act: -0.0001

Data Index: 1124457 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.6202. Min Act: -0.0000

Data Index: 707419 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.8561. Min Act: -0.0001

Data Index: 115720 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.6948. Min Act: -0.0000

Data Index: 818626 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.5478. Min Act: -0.0001

Data Index: 491511 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.9024. Min Act: -0.0001

Data Index: 389593 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.7777. Min Act: -0.0000

Data Index: 1325424 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.6248. Min Act: -0.0001

Data Index: 808672 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.6079. Min Act: -0.0000

Data Index: 111264 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.7324. Min Act: -0.0001

Data Index: 1203004 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.9763. Min Act: -0.0000

Data Index: 499689 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.4877. Min Act: -0.0001

Data Index: 997343 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.4784. Min Act: -0.0000

Data Index: 738006 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.5711. Min Act: -0.0000

Data Index: 132602 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.5782. Min Act: -0.0000

Data Index: 1272933 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.5086. Min Act: -0.0000

Data Index: 718922 (C4 (Web Text))

Max Activating Token Index: 708