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

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

Neuron 4637 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: 2.4188. Min Range: -2.4188

Max Act: 2.4065. Min Act: -0.0000

Data Index: 889779 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 2.4188. Min Range: -2.4188

Max Act: 2.4188. Min Act: -0.0000

Data Index: 120213 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 2.4188. Min Range: -2.4188

Max Act: 2.2651. Min Act: -0.0000

Data Index: 528616 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 2.4188. Min Range: -2.4188

Max Act: 2.2157. Min Act: -0.0000

Data Index: 461221 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 2.4188. Min Range: -2.4188

Max Act: 2.0379. Min Act: -0.0000

Data Index: 249952 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.8465. Min Act: -0.0000

Data Index: 970290 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.8067. Min Act: -0.0000

Data Index: 559819 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.7247. Min Act: -0.0000

Data Index: 5685 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.7700. Min Act: -0.0000

Data Index: 147573 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.7684. Min Act: -0.0000

Data Index: 230897 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.6668. Min Act: -0.0000

Data Index: 549205 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.6423. Min Act: -0.0000

Data Index: 25265 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.8201. Min Act: -0.0000

Data Index: 766570 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.7197. Min Act: -0.0000

Data Index: 712861 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.7046. Min Act: -0.0000

Data Index: 705912 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.7040. Min Act: -0.0000

Data Index: 259267 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.6436. Min Act: -0.0000

Data Index: 922140 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.6251. Min Act: -0.0000

Data Index: 313428 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.5978. Min Act: -0.0000

Data Index: 253400 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 2.4188. Min Range: -2.4188

Max Act: 1.6809. Min Act: -0.0000

Data Index: 315640 (C4 (Web Text))

Max Activating Token Index: 898