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

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

Neuron 556 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.2313. Min Act: -0.0001

Data Index: 848064 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.2101. Min Act: -0.0001

Data Index: 1217075 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.2158. Min Act: -0.0001

Data Index: 809956 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1105803 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1901. Min Act: -0.0001

Data Index: 772028 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.2010. Min Act: -0.0001

Data Index: 741130 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1927. Min Act: -0.0001

Data Index: 896445 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1957. Min Act: -0.0001

Data Index: 497154 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1853. Min Act: -0.0001

Data Index: 32680 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1989. Min Act: -0.0001

Data Index: 1096514 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1929. Min Act: -0.0001

Data Index: 448562 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1951. Min Act: -0.0001

Data Index: 300118 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1960. Min Act: -0.0001

Data Index: 178825 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.2157. Min Act: -0.0001

Data Index: 1075504 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1564. Min Act: -0.0001

Data Index: 109704 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1981. Min Act: -0.0001

Data Index: 683833 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1007171 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.2020. Min Act: -0.0001

Data Index: 1017001 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1846. Min Act: -0.0001

Data Index: 558956 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1847. Min Act: -0.0001

Data Index: 746256 (C4 (Web Text))

Max Activating Token Index: 30