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

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

Neuron 4011 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3014. Min Range: -3.3014

Max Act: 3.1066. Min Act: -0.0002

Data Index: 1312647 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 3.3014. Min Range: -3.3014

Max Act: 3.3014. Min Act: -0.0001

Data Index: 777362 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 3.3014. Min Range: -3.3014

Max Act: 2.6334. Min Act: -0.0001

Data Index: 353531 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 3.3014. Min Range: -3.3014

Max Act: 2.1674. Min Act: -0.0001

Data Index: 628134 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 3.3014. Min Range: -3.3014

Max Act: 2.3866. Min Act: -0.0001

Data Index: 836371 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 3.3014. Min Range: -3.3014

Max Act: 2.3142. Min Act: -0.0002

Data Index: 171174 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 3.3014. Min Range: -3.3014

Max Act: 2.0553. Min Act: -0.0002

Data Index: 475753 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 3.3014. Min Range: -3.3014

Max Act: 1.9198. Min Act: -0.0002

Data Index: 588622 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 3.3014. Min Range: -3.3014

Max Act: 1.9429. Min Act: -0.0001

Data Index: 370861 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 3.3014. Min Range: -3.3014

Max Act: 2.0704. Min Act: -0.0002

Data Index: 418789 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 3.3014. Min Range: -3.3014

Max Act: 1.8982. Min Act: -0.0001

Data Index: 684290 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 3.3014. Min Range: -3.3014

Max Act: 1.8896. Min Act: -0.0002

Data Index: 720948 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 3.3014. Min Range: -3.3014

Max Act: 1.8026. Min Act: -0.0001

Data Index: 120145 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 3.3014. Min Range: -3.3014

Max Act: 1.6734. Min Act: -0.0001

Data Index: 423081 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 3.3014. Min Range: -3.3014

Max Act: 1.7220. Min Act: -0.0001

Data Index: 488711 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 3.3014. Min Range: -3.3014

Max Act: 1.7788. Min Act: -0.0001

Data Index: 1327871 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 3.3014. Min Range: -3.3014

Max Act: 1.7385. Min Act: -0.0001

Data Index: 369761 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 3.3014. Min Range: -3.3014

Max Act: 1.7469. Min Act: -0.0001

Data Index: 100460 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 3.3014. Min Range: -3.3014

Max Act: 1.5884. Min Act: -0.0001

Data Index: 196941 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 3.3014. Min Range: -3.3014

Max Act: 1.6692. Min Act: -0.0002

Data Index: 967137 (C4 (Web Text))

Max Activating Token Index: 573