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

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

Neuron 194 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.8162. Min Act: -0.0001

Data Index: 1213166 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7438. Min Act: -0.0001

Data Index: 378835 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.8616. Min Act: -0.0001

Data Index: 1061528 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7532. Min Act: -0.0001

Data Index: 1086725 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7943. Min Act: -0.0001

Data Index: 410916 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7502. Min Act: -0.0001

Data Index: 1119903 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7577. Min Act: -0.0002

Data Index: 1208841 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7851. Min Act: -0.0001

Data Index: 785692 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7274. Min Act: -0.0001

Data Index: 1050296 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7976. Min Act: -0.0001

Data Index: 604453 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7387. Min Act: -0.0001

Data Index: 22084 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.6792. Min Act: -0.0001

Data Index: 105659 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7335. Min Act: -0.0001

Data Index: 1271049 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7944. Min Act: -0.0001

Data Index: 1317439 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7191. Min Act: -0.0001

Data Index: 1277513 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7136. Min Act: -0.0001

Data Index: 1106981 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7481. Min Act: -0.0001

Data Index: 165042 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7261. Min Act: -0.0001

Data Index: 792908 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.6985. Min Act: -0.0001

Data Index: 584067 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.8616. Min Range: -0.8616

Max Act: 0.7065. Min Act: -0.0001

Data Index: 194833 (C4 (Web Text))

Max Activating Token Index: 21