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

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

Neuron 459 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.6522. Min Act: -0.0000

Data Index: 1174611 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.5343. Min Act: -0.0000

Data Index: 1517334 (Python Code)

Max Activating Token Index: 880

Text #2

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.4293. Min Act: -0.0000

Data Index: 1455345 (Python Code)

Max Activating Token Index: 163

Text #3

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.4166. Min Act: -0.0000

Data Index: 1595298 (Python Code)

Max Activating Token Index: 394

Text #4

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.5239. Min Act: -0.0000

Data Index: 1533592 (Python Code)

Max Activating Token Index: 159

Text #5

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.2640. Min Act: -0.0000

Data Index: 654056 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.4270. Min Act: -0.0000

Data Index: 479726 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1537949 (Python Code)

Max Activating Token Index: 740

Text #8

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.3227. Min Act: -0.0000

Data Index: 1170928 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.1486. Min Act: -0.0000

Data Index: 251144 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1415698 (Python Code)

Max Activating Token Index: 606

Text #11

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.3405. Min Act: -0.0000

Data Index: 554473 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1508841 (Python Code)

Max Activating Token Index: 315

Text #13

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.1977. Min Act: -0.0000

Data Index: 814941 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1590054 (Python Code)

Max Activating Token Index: 184

Text #15

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1365586 (Python Code)

Max Activating Token Index: 313

Text #16

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.2070. Min Act: -0.0000

Data Index: 1152334 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.1365. Min Act: -0.0000

Data Index: 1637054 (Python Code)

Max Activating Token Index: 427

Text #18

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.0044. Min Act: -0.0000

Data Index: 869044 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.6522. Min Range: -1.6522

Max Act: 1.1798. Min Act: -0.0000

Data Index: 613606 (C4 (Web Text))

Max Activating Token Index: 691