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

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

Neuron 1181 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1233154 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1234. Min Act: -0.0001

Data Index: 999864 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1259487 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1080. Min Act: -0.0001

Data Index: 940284 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1082367 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1091. Min Act: -0.0001

Data Index: 969403 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1176387 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1123. Min Act: -0.0001

Data Index: 528694 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1077. Min Act: -0.0001

Data Index: 820172 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1038. Min Act: -0.0001

Data Index: 689910 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1020335 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1044. Min Act: -0.0001

Data Index: 728287 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0975. Min Act: -0.0001

Data Index: 616873 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1045. Min Act: -0.0001

Data Index: 181521 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0972. Min Act: -0.0001

Data Index: 771586 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0964. Min Act: -0.0001

Data Index: 607433 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0999. Min Act: -0.0001

Data Index: 836638 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1197443 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.1035. Min Act: -0.0001

Data Index: 273918 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.1268. Min Range: -0.1268

Max Act: 0.0873. Min Act: -0.0001

Data Index: 799567 (C4 (Web Text))

Max Activating Token Index: 638