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

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

Neuron 742 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.8083. Min Act: -0.0003

Data Index: 221572 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7068. Min Act: -0.0003

Data Index: 619236 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7412. Min Act: -0.0003

Data Index: 808528 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7805. Min Act: -0.0003

Data Index: 200421 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7190. Min Act: -0.0003

Data Index: 630371 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6261. Min Act: -0.0003

Data Index: 108225 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7186. Min Act: -0.0003

Data Index: 562604 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.7188. Min Act: -0.0003

Data Index: 834868 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6810. Min Act: -0.0003

Data Index: 806240 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6785. Min Act: -0.0003

Data Index: 643428 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6400. Min Act: -0.0003

Data Index: 1017983 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6451. Min Act: -0.0003

Data Index: 947944 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6987. Min Act: -0.0003

Data Index: 1067190 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6367. Min Act: -0.0003

Data Index: 548895 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6638. Min Act: -0.0003

Data Index: 889280 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6529. Min Act: -0.0003

Data Index: 936257 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5818. Min Act: -0.0003

Data Index: 339262 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6359. Min Act: -0.0003

Data Index: 1228564 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6333. Min Act: -0.0003

Data Index: 522949 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6710. Min Act: -0.0003

Data Index: 342007 (C4 (Web Text))

Max Activating Token Index: 227