Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4512 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.7779. Min Act: -0.0000

Data Index: 568196 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.6293. Min Act: -0.0000

Data Index: 369809 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.6297. Min Act: -0.0000

Data Index: 471074 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1525223 (Python Code)

Max Activating Token Index: 922

Text #4

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.6033. Min Act: -0.0000

Data Index: 904706 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.6014. Min Act: 0.0000

Data Index: 1030132 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1387379 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5662. Min Act: -0.0000

Data Index: 629133 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5506. Min Act: -0.0000

Data Index: 908076 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1310970 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1095353 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5363. Min Act: -0.0000

Data Index: 886503 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5382. Min Act: -0.0000

Data Index: 413806 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5114. Min Act: -0.0000

Data Index: 997086 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5298. Min Act: -0.0000

Data Index: 964022 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1337074 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.4924. Min Act: -0.0000

Data Index: 343756 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5006. Min Act: -0.0000

Data Index: 963336 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.4953. Min Act: -0.0000

Data Index: 36509 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5132. Min Act: -0.0000

Data Index: 902267 (C4 (Web Text))

Max Activating Token Index: 607