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

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

Neuron 2873 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: 0.7476. Min Range: -0.7476

Max Act: 0.7217. Min Act: -0.0000

Data Index: 291344 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.7420. Min Act: -0.0000

Data Index: 970791 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.7476. Min Act: -0.0000

Data Index: 263324 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6270. Min Act: -0.0000

Data Index: 371197 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1333180 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6362. Min Act: -0.0000

Data Index: 118619 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6331. Min Act: -0.0000

Data Index: 51988 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6593. Min Act: -0.0000

Data Index: 256717 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6256. Min Act: -0.0000

Data Index: 751449 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5969. Min Act: -0.0000

Data Index: 316262 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6123. Min Act: -0.0000

Data Index: 704295 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5921. Min Act: -0.0000

Data Index: 106061 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6100. Min Act: -0.0000

Data Index: 490225 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6068. Min Act: -0.0000

Data Index: 738240 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5848. Min Act: -0.0000

Data Index: 751073 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1102941 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1094123 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1304335 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5687. Min Act: -0.0000

Data Index: 458529 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5787. Min Act: -0.0000

Data Index: 315817 (C4 (Web Text))

Max Activating Token Index: 714