Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2944 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5082. Min Range: -2.5082

Max Act: 2.5082. Min Act: -0.0000

Data Index: 1492919 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 2.5082. Min Range: -2.5082

Max Act: 2.2836. Min Act: -0.0001

Data Index: 1242255 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 2.5082. Min Range: -2.5082

Max Act: 2.2115. Min Act: -0.0000

Data Index: 1435276 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 2.5082. Min Range: -2.5082

Max Act: 2.2842. Min Act: -0.0000

Data Index: 1533627 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 2.5082. Min Range: -2.5082

Max Act: 2.0254. Min Act: -0.0000

Data Index: 1430148 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.3725. Min Act: -0.0000

Data Index: 1561125 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.7582. Min Act: -0.0001

Data Index: 1437593 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1438774 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 2.5082. Min Range: -2.5082

Max Act: 2.3946. Min Act: -0.0001

Data Index: 913655 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.9084. Min Act: -0.0000

Data Index: 1571674 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.9032. Min Act: -0.0000

Data Index: 1630202 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.8869. Min Act: -0.0001

Data Index: 1414011 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.6022. Min Act: -0.0000

Data Index: 1598169 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.7815. Min Act: -0.0000

Data Index: 594643 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.9175. Min Act: -0.0000

Data Index: 1389958 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.6850. Min Act: -0.0001

Data Index: 1570497 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.5121. Min Act: -0.0000

Data Index: 1414851 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 2.5082. Min Range: -2.5082

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1467378 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.7363. Min Act: -0.0001

Data Index: 1393861 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 2.5082. Min Range: -2.5082

Max Act: 1.7050. Min Act: -0.0001

Data Index: 1553611 (Python Code)

Max Activating Token Index: 1023