Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3202 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.8949. Min Act: -0.0000

Data Index: 828213 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.6955. Min Act: -0.0000

Data Index: 573757 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.8083. Min Act: -0.0000

Data Index: 956235 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.7995. Min Act: -0.0000

Data Index: 581267 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.6506. Min Act: -0.0000

Data Index: 296900 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.6949. Min Act: -0.0000

Data Index: 169882 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1036997 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.5205. Min Act: -0.0000

Data Index: 619036 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.5257. Min Act: -0.0000

Data Index: 882120 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.5127. Min Act: -0.0000

Data Index: 612401 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.5165. Min Act: -0.0000

Data Index: 76666 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1240862 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.4134. Min Act: 0.0000

Data Index: 367033 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.3450. Min Act: -0.0000

Data Index: 821670 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.2945. Min Act: 0.0000

Data Index: 837443 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.3113. Min Act: 0.0000

Data Index: 1059795 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.3043. Min Act: 0.0000

Data Index: 688757 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.3377. Min Act: -0.0000

Data Index: 276276 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.3314. Min Act: -0.0000

Data Index: 889341 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.8949. Min Range: -0.8949

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1385321 (Python Code)

Max Activating Token Index: 465