Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2461 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6670. Min Act: -0.0000

Data Index: 199333 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6478. Min Act: -0.0001

Data Index: 133225 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6855. Min Act: -0.0001

Data Index: 1130340 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6493. Min Act: -0.0001

Data Index: 802314 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6529. Min Act: -0.0001

Data Index: 344024 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6271. Min Act: -0.0001

Data Index: 493994 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6403. Min Act: -0.0001

Data Index: 73808 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1283535 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5952. Min Act: -0.0001

Data Index: 960673 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5939. Min Act: -0.0001

Data Index: 396506 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5980. Min Act: -0.0001

Data Index: 46844 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5792. Min Act: -0.0001

Data Index: 1067072 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5323. Min Act: -0.0001

Data Index: 1159669 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.6380. Min Act: -0.0001

Data Index: 278218 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5593. Min Act: -0.0001

Data Index: 1074899 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5423. Min Act: -0.0001

Data Index: 1183926 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5420. Min Act: -0.0000

Data Index: 663754 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.3991. Min Act: -0.0001

Data Index: 696894 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5895. Min Act: -0.0001

Data Index: 229526 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.6855. Min Range: -0.6855

Max Act: 0.5292. Min Act: -0.0001

Data Index: 1174606 (C4 (Web Text))

Max Activating Token Index: 8