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

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

Neuron 6132 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.4283. Min Act: -0.0000

Data Index: 410681 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.2301. Min Act: -0.0000

Data Index: 656310 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.1369. Min Act: -0.0000

Data Index: 150406 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.1379. Min Act: -0.0000

Data Index: 777208 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.1797. Min Act: -0.0000

Data Index: 1100829 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 1.4283. Min Range: -1.4283

Max Act: 1.0081. Min Act: -0.0000

Data Index: 988433 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.9394. Min Act: -0.0000

Data Index: 506035 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.9280. Min Act: -0.0000

Data Index: 174607 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1049314 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.7235. Min Act: -0.0000

Data Index: 988 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.7215. Min Act: -0.0000

Data Index: 576295 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1348822 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.6693. Min Act: -0.0000

Data Index: 438825 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.6413. Min Act: -0.0000

Data Index: 36650 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.5631. Min Act: -0.0000

Data Index: 118842 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.5124. Min Act: -0.0000

Data Index: 582214 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.4870. Min Act: -0.0000

Data Index: 727892 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.4937. Min Act: -0.0000

Data Index: 973829 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1153791 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 1.4283. Min Range: -1.4283

Max Act: 0.5264. Min Act: -0.0000

Data Index: 15442 (C4 (Web Text))

Max Activating Token Index: 41