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

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

Neuron 1354 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: 1.0476. Min Range: -1.0476

Max Act: 0.9019. Min Act: -0.0002

Data Index: 745642 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.8607. Min Act: -0.0002

Data Index: 125232 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 1.0476. Min Range: -1.0476

Max Act: 1.0476. Min Act: -0.0001

Data Index: 1146853 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.7998. Min Act: -0.0001

Data Index: 823480 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.8188. Min Act: -0.0002

Data Index: 292091 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.7502. Min Act: -0.0001

Data Index: 873841 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.8837. Min Act: -0.0001

Data Index: 972245 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.7973. Min Act: -0.0001

Data Index: 507069 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.7360. Min Act: -0.0001

Data Index: 1236214 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.7522. Min Act: -0.0001

Data Index: 86434 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.7037. Min Act: -0.0002

Data Index: 583325 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.7729. Min Act: -0.0001

Data Index: 1272049 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.7927. Min Act: -0.0001

Data Index: 1339149 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.6908. Min Act: -0.0001

Data Index: 1192702 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.6266. Min Act: -0.0001

Data Index: 520904 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.6869. Min Act: -0.0001

Data Index: 162246 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.7027. Min Act: -0.0001

Data Index: 874765 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.6767. Min Act: -0.0002

Data Index: 471286 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.6461. Min Act: -0.0001

Data Index: 1037431 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.0476. Min Range: -1.0476

Max Act: 0.6714. Min Act: -0.0002

Data Index: 154314 (C4 (Web Text))

Max Activating Token Index: 59