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

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

Neuron 1066 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: 0.6980. Min Range: -0.6980

Max Act: 0.6757. Min Act: -0.0002

Data Index: 1347963 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.6500. Min Act: -0.0001

Data Index: 784102 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.6755. Min Act: -0.0002

Data Index: 68229 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.6565. Min Act: -0.0002

Data Index: 1256442 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.6491. Min Act: -0.0001

Data Index: 966990 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.6980. Min Act: -0.0002

Data Index: 1329323 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.6477. Min Act: -0.0001

Data Index: 670673 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.6316. Min Act: -0.0002

Data Index: 33218 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.6488. Min Act: -0.0002

Data Index: 1079598 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.6220. Min Act: -0.0001

Data Index: 1217210 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.5984. Min Act: -0.0001

Data Index: 1347811 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.6345. Min Act: -0.0001

Data Index: 828541 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.6342. Min Act: -0.0001

Data Index: 819903 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.5926. Min Act: -0.0001

Data Index: 849812 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.5906. Min Act: -0.0001

Data Index: 1041839 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.6224. Min Act: -0.0001

Data Index: 376426 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.5799. Min Act: -0.0002

Data Index: 966416 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.5977. Min Act: -0.0002

Data Index: 1330929 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.5993. Min Act: -0.0001

Data Index: 162669 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.6980. Min Range: -0.6980

Max Act: 0.5950. Min Act: -0.0002

Data Index: 255811 (C4 (Web Text))

Max Activating Token Index: 128