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

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

Neuron 5461 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: 1.3083. Min Range: -1.3083

Max Act: 1.3083. Min Act: -0.0001

Data Index: 1221583 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.2547. Min Act: -0.0001

Data Index: 1625347 (Python Code)

Max Activating Token Index: 198

Text #2

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1511. Min Act: -0.0001

Data Index: 1410295 (Python Code)

Max Activating Token Index: 746

Text #3

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1927. Min Act: -0.0001

Data Index: 1024298 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.2030. Min Act: -0.0001

Data Index: 630407 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.2027. Min Act: -0.0001

Data Index: 1600886 (Python Code)

Max Activating Token Index: 225

Text #6

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1938. Min Act: -0.0001

Data Index: 1370675 (Python Code)

Max Activating Token Index: 195

Text #7

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1268. Min Act: -0.0001

Data Index: 1480063 (Python Code)

Max Activating Token Index: 245

Text #8

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1491. Min Act: -0.0001

Data Index: 1272612 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9486. Min Act: -0.0001

Data Index: 298298 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0506. Min Act: -0.0001

Data Index: 27610 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1001. Min Act: -0.0001

Data Index: 1364927 (Python Code)

Max Activating Token Index: 599

Text #12

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0533. Min Act: -0.0001

Data Index: 1617722 (Python Code)

Max Activating Token Index: 204

Text #13

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0972. Min Act: -0.0001

Data Index: 1588621 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0879. Min Act: -0.0001

Data Index: 538885 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0814. Min Act: -0.0001

Data Index: 1408794 (Python Code)

Max Activating Token Index: 226

Text #16

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0751. Min Act: -0.0001

Data Index: 499983 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0852. Min Act: -0.0001

Data Index: 1495444 (Python Code)

Max Activating Token Index: 932

Text #18

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0680. Min Act: -0.0001

Data Index: 58764 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1419. Min Act: -0.0001

Data Index: 745479 (C4 (Web Text))

Max Activating Token Index: 894