Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3968 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.2248. Min Act: -0.0002

Data Index: 794104 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.1965. Min Act: -0.0002

Data Index: 1200741 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.1807. Min Act: -0.0002

Data Index: 1338859 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.1191. Min Act: -0.0002

Data Index: 352677 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.1803. Min Act: -0.0002

Data Index: 776078 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.1018. Min Act: -0.0002

Data Index: 1118883 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.1058. Min Act: -0.0002

Data Index: 783722 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.0715. Min Act: -0.0002

Data Index: 290561 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.0858. Min Act: -0.0002

Data Index: 473116 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.1080. Min Act: -0.0001

Data Index: 347976 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.0280. Min Act: -0.0002

Data Index: 557020 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.0435. Min Act: -0.0002

Data Index: 734158 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.0655. Min Act: -0.0001

Data Index: 983685 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.0329. Min Act: -0.0001

Data Index: 1107476 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.8900. Min Act: -0.0002

Data Index: 400850 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.0585. Min Act: -0.0001

Data Index: 479010 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.0249. Min Act: -0.0002

Data Index: 699138 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9574. Min Act: -0.0001

Data Index: 150573 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9682. Min Act: -0.0002

Data Index: 996840 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.0888. Min Act: -0.0002

Data Index: 10324 (C4 (Web Text))

Max Activating Token Index: 313