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

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

Neuron 117 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.6997. Min Act: -0.0000

Data Index: 287478 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1221534 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.7010. Min Act: -0.0000

Data Index: 119183 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1625175 (Python Code)

Max Activating Token Index: 982

Text #4

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.6843. Min Act: -0.0000

Data Index: 866514 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5963. Min Act: -0.0000

Data Index: 338459 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1168486 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5732. Min Act: -0.0000

Data Index: 767357 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1172849 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5897. Min Act: -0.0000

Data Index: 439043 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5425. Min Act: 0.0000

Data Index: 675791 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5429. Min Act: -0.0000

Data Index: 509020 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5598. Min Act: -0.0000

Data Index: 740673 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5191. Min Act: -0.0000

Data Index: 920711 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5374. Min Act: -0.0000

Data Index: 164882 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1000515 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1057308 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.6015. Min Act: -0.0000

Data Index: 492205 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5257. Min Act: -0.0000

Data Index: 774348 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5261. Min Act: -0.0000

Data Index: 870835 (C4 (Web Text))

Max Activating Token Index: 278