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

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

Neuron 1450 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.6192. Min Act: -0.0000

Data Index: 154156 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1271809 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.5479. Min Act: -0.0000

Data Index: 816212 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.5436. Min Act: -0.0000

Data Index: 662112 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.5507. Min Act: -0.0000

Data Index: 545131 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.5413. Min Act: -0.0000

Data Index: 223987 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.5174. Min Act: -0.0000

Data Index: 142108 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.5121. Min Act: -0.0000

Data Index: 199037 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.5101. Min Act: -0.0000

Data Index: 997218 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4831. Min Act: -0.0000

Data Index: 930155 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.5059. Min Act: -0.0000

Data Index: 946689 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4596. Min Act: -0.0000

Data Index: 92266 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4499. Min Act: -0.0000

Data Index: 351908 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4664. Min Act: -0.0000

Data Index: 256603 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1117916 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4530. Min Act: -0.0000

Data Index: 661533 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4620. Min Act: -0.0000

Data Index: 281865 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4350. Min Act: -0.0000

Data Index: 378269 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4457. Min Act: -0.0000

Data Index: 759502 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4320. Min Act: -0.0000

Data Index: 52764 (C4 (Web Text))

Max Activating Token Index: 759