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

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

Neuron 4826 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0578. Min Range: -6.0578

Max Act: 6.0501. Min Act: -0.0000

Data Index: 1237152 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 6.0578. Min Range: -6.0578

Max Act: 6.0421. Min Act: -0.0000

Data Index: 427605 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.9088. Min Act: -0.0001

Data Index: 452096 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.9024. Min Act: -0.0001

Data Index: 359814 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.7067. Min Act: -0.0000

Data Index: 461251 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.8758. Min Act: -0.0000

Data Index: 142312 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.8781. Min Act: -0.0000

Data Index: 944209 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.8781. Min Act: -0.0001

Data Index: 425287 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.8928. Min Act: -0.0000

Data Index: 1123857 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 6.0578. Min Range: -6.0578

Max Act: 6.0578. Min Act: -0.0001

Data Index: 729507 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.8821. Min Act: -0.0000

Data Index: 849515 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 6.0578. Min Range: -6.0578

Max Act: 6.0351. Min Act: -0.0000

Data Index: 344028 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.7563. Min Act: -0.0001

Data Index: 103376 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.7094. Min Act: -0.0000

Data Index: 665665 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.7100. Min Act: -0.0001

Data Index: 98293 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.6921. Min Act: -0.0000

Data Index: 491325 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.8783. Min Act: -0.0000

Data Index: 651740 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.6878. Min Act: -0.0001

Data Index: 1224996 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 6.0578. Min Range: -6.0578

Max Act: 6.0489. Min Act: -0.0000

Data Index: 1222590 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 6.0578. Min Range: -6.0578

Max Act: 5.9179. Min Act: -0.0001

Data Index: 483070 (C4 (Web Text))

Max Activating Token Index: 206