Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3736 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1184. Min Range: -1.1184

Max Act: 1.1184. Min Act: -0.0001

Data Index: 582787 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 1.1184. Min Range: -1.1184

Max Act: 1.0154. Min Act: -0.0001

Data Index: 78624 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 1.1184. Min Range: -1.1184

Max Act: 1.0454. Min Act: -0.0001

Data Index: 1097137 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 1.1184. Min Range: -1.1184

Max Act: 1.0064. Min Act: -0.0000

Data Index: 868065 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9894. Min Act: -0.0000

Data Index: 738392 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9485. Min Act: -0.0001

Data Index: 499237 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 1.1184. Min Range: -1.1184

Max Act: 1.0003. Min Act: -0.0001

Data Index: 1093737 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9416. Min Act: -0.0001

Data Index: 266769 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9353. Min Act: -0.0001

Data Index: 1328151 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1154782 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9108. Min Act: -0.0001

Data Index: 687019 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9175. Min Act: -0.0001

Data Index: 238385 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8992. Min Act: -0.0001

Data Index: 320803 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8481. Min Act: -0.0001

Data Index: 1203384 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8661. Min Act: -0.0000

Data Index: 646997 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.7826. Min Act: -0.0001

Data Index: 1158960 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8087. Min Act: -0.0000

Data Index: 737137 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8311. Min Act: -0.0001

Data Index: 578459 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.7743. Min Act: -0.0001

Data Index: 374398 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8111. Min Act: -0.0000

Data Index: 381477 (C4 (Web Text))

Max Activating Token Index: 880