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

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

Neuron 1572 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.3988. Min Act: -0.0000

Data Index: 1413348 (Python Code)

Max Activating Token Index: 470

Text #1

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.4693. Min Act: -0.0000

Data Index: 1499104 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.3219. Min Act: -0.0000

Data Index: 1527712 (Python Code)

Max Activating Token Index: 1015

Text #3

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.3189. Min Act: -0.0000

Data Index: 1507180 (Python Code)

Max Activating Token Index: 403

Text #4

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1423288 (Python Code)

Max Activating Token Index: 348

Text #5

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1460973 (Python Code)

Max Activating Token Index: 597

Text #6

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1981. Min Act: -0.0000

Data Index: 1549273 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.2337. Min Act: -0.0000

Data Index: 1411872 (Python Code)

Max Activating Token Index: 803

Text #8

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1888. Min Act: -0.0000

Data Index: 1394183 (Python Code)

Max Activating Token Index: 706

Text #9

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1633753 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1581768 (Python Code)

Max Activating Token Index: 1009

Text #11

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1354. Min Act: -0.0000

Data Index: 1370589 (Python Code)

Max Activating Token Index: 151

Text #12

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1601. Min Act: -0.0000

Data Index: 1360504 (Python Code)

Max Activating Token Index: 130

Text #13

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1651847 (Python Code)

Max Activating Token Index: 200

Text #14

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1616200 (Python Code)

Max Activating Token Index: 601

Text #15

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.0617. Min Act: -0.0000

Data Index: 1572609 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1540595 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1494078 (Python Code)

Max Activating Token Index: 900

Text #18

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1464835 (Python Code)

Max Activating Token Index: 227

Text #19

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.0347. Min Act: -0.0000

Data Index: 1386201 (Python Code)

Max Activating Token Index: 609