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

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

Neuron 1896 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.9822. Min Act: -0.0000

Data Index: 1322705 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 2.9968. Min Range: -2.9968

Max Act: 1.9526. Min Act: -0.0000

Data Index: 177616 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.9968. Min Act: -0.0000

Data Index: 517226 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.8935. Min Act: -0.0000

Data Index: 648641 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.2388. Min Act: -0.0000

Data Index: 942407 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.3565. Min Act: -0.0000

Data Index: 50718 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.4034. Min Act: -0.0000

Data Index: 948615 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.1703. Min Act: -0.0000

Data Index: 990979 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 2.9968. Min Range: -2.9968

Max Act: 0.9784. Min Act: -0.0000

Data Index: 908374 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.5225. Min Act: -0.0000

Data Index: 912972 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.3689. Min Act: -0.0000

Data Index: 743673 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.3385. Min Act: -0.0000

Data Index: 808601 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.1008. Min Act: -0.0000

Data Index: 927526 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.1517. Min Act: -0.0000

Data Index: 865749 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.5091. Min Act: -0.0000

Data Index: 785856 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 2.9968. Min Range: -2.9968

Max Act: 1.5919. Min Act: -0.0000

Data Index: 427620 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.5680. Min Act: -0.0000

Data Index: 1161839 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 2.9968. Min Range: -2.9968

Max Act: 1.9314. Min Act: -0.0000

Data Index: 1311792 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 2.9968. Min Range: -2.9968

Max Act: 1.7895. Min Act: -0.0000

Data Index: 133453 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 2.9968. Min Range: -2.9968

Max Act: 1.9350. Min Act: -0.0000

Data Index: 918746 (C4 (Web Text))

Max Activating Token Index: 22