Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1639 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1116. Min Act: -0.0001

Data Index: 454268 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1069. Min Act: -0.0001

Data Index: 445469 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1009. Min Act: -0.0001

Data Index: 128790 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1042. Min Act: -0.0001

Data Index: 253739 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1219708 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1034. Min Act: -0.0001

Data Index: 343341 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1134959 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1301272 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1022. Min Act: -0.0001

Data Index: 802741 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1016. Min Act: -0.0001

Data Index: 516414 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1053. Min Act: -0.0001

Data Index: 789512 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1280682 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1014. Min Act: -0.0001

Data Index: 313188 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1009. Min Act: -0.0001

Data Index: 509631 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1009. Min Act: -0.0001

Data Index: 1270419 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0974. Min Act: -0.0001

Data Index: 537774 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1099706 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1045193 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1003. Min Act: -0.0001

Data Index: 764525 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1041. Min Act: -0.0001

Data Index: 26422 (C4 (Web Text))

Max Activating Token Index: 587