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

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

Neuron 4926 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: 1.9869. Min Range: -1.9869

Max Act: 1.9869. Min Act: -0.0001

Data Index: 1396781 (Python Code)

Max Activating Token Index: 989

Text #1

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.6410. Min Act: -0.0001

Data Index: 1362392 (Python Code)

Max Activating Token Index: 142

Text #2

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.4964. Min Act: -0.0001

Data Index: 1371056 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.6258. Min Act: -0.0001

Data Index: 1445843 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.5678. Min Act: -0.0001

Data Index: 1395993 (Python Code)

Max Activating Token Index: 527

Text #5

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.3381. Min Act: -0.0001

Data Index: 1635805 (Python Code)

Max Activating Token Index: 900

Text #6

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.4690. Min Act: -0.0001

Data Index: 1438484 (Python Code)

Max Activating Token Index: 1003

Text #7

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.3541. Min Act: -0.0000

Data Index: 1582862 (Python Code)

Max Activating Token Index: 349

Text #8

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.4628. Min Act: -0.0001

Data Index: 1505630 (Python Code)

Max Activating Token Index: 894

Text #9

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.4142. Min Act: -0.0001

Data Index: 1558485 (Python Code)

Max Activating Token Index: 502

Text #10

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.3896. Min Act: -0.0000

Data Index: 1651854 (Python Code)

Max Activating Token Index: 486

Text #11

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.3007. Min Act: -0.0001

Data Index: 1578322 (Python Code)

Max Activating Token Index: 349

Text #12

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.2255. Min Act: -0.0001

Data Index: 1380002 (Python Code)

Max Activating Token Index: 693

Text #13

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.2890. Min Act: -0.0001

Data Index: 1540834 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.1835. Min Act: -0.0001

Data Index: 1374047 (Python Code)

Max Activating Token Index: 901

Text #15

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.3470. Min Act: -0.0001

Data Index: 1489968 (Python Code)

Max Activating Token Index: 326

Text #16

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.2637. Min Act: -0.0001

Data Index: 1604532 (Python Code)

Max Activating Token Index: 347

Text #17

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.2086. Min Act: -0.0001

Data Index: 1602399 (Python Code)

Max Activating Token Index: 220

Text #18

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.2732. Min Act: -0.0001

Data Index: 1438383 (Python Code)

Max Activating Token Index: 803

Text #19

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.3089. Min Act: -0.0001

Data Index: 1510967 (Python Code)

Max Activating Token Index: 83