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

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

Neuron 4699 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: 0.5630. Min Range: -0.5630

Max Act: 0.5630. Min Act: -0.0001

Data Index: 1605562 (Python Code)

Max Activating Token Index: 873

Text #1

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.5461. Min Act: -0.0001

Data Index: 1568044 (Python Code)

Max Activating Token Index: 965

Text #2

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.5226. Min Act: -0.0001

Data Index: 1655652 (Python Code)

Max Activating Token Index: 939

Text #3

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.5127. Min Act: -0.0001

Data Index: 1646800 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.5204. Min Act: -0.0001

Data Index: 1393959 (Python Code)

Max Activating Token Index: 989

Text #5

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.5113. Min Act: -0.0001

Data Index: 1367577 (Python Code)

Max Activating Token Index: 855

Text #6

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4512. Min Act: -0.0001

Data Index: 1522688 (Python Code)

Max Activating Token Index: 601

Text #7

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4664. Min Act: -0.0001

Data Index: 1547134 (Python Code)

Max Activating Token Index: 490

Text #8

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4386. Min Act: -0.0001

Data Index: 1591614 (Python Code)

Max Activating Token Index: 450

Text #9

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4064. Min Act: -0.0001

Data Index: 1610485 (Python Code)

Max Activating Token Index: 409

Text #10

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4101. Min Act: -0.0001

Data Index: 1548812 (Python Code)

Max Activating Token Index: 249

Text #11

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4318. Min Act: -0.0001

Data Index: 1621657 (Python Code)

Max Activating Token Index: 494

Text #12

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4065. Min Act: -0.0001

Data Index: 1522514 (Python Code)

Max Activating Token Index: 408

Text #13

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4033. Min Act: -0.0001

Data Index: 1449048 (Python Code)

Max Activating Token Index: 98

Text #14

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.3972. Min Act: -0.0001

Data Index: 1649214 (Python Code)

Max Activating Token Index: 461

Text #15

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.3671. Min Act: -0.0001

Data Index: 1629870 (Python Code)

Max Activating Token Index: 59

Text #16

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.3546. Min Act: -0.0001

Data Index: 1531245 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.3608. Min Act: -0.0001

Data Index: 892390 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.3548. Min Act: -0.0001

Data Index: 1429808 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.3900. Min Act: -0.0001

Data Index: 1537629 (Python Code)

Max Activating Token Index: 93