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

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

Neuron 1198 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9731. Min Act: -0.0000

Data Index: 287003 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 1.0294. Min Range: -1.0294

Max Act: 1.0294. Min Act: -0.0001

Data Index: 430152 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9430. Min Act: -0.0000

Data Index: 405159 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9865. Min Act: -0.0000

Data Index: 431418 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1303057 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9968. Min Act: -0.0001

Data Index: 912629 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9705. Min Act: -0.0001

Data Index: 147079 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8789. Min Act: -0.0001

Data Index: 1071273 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8779. Min Act: -0.0001

Data Index: 238290 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9006. Min Act: -0.0000

Data Index: 890030 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9405. Min Act: -0.0001

Data Index: 1093891 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9681. Min Act: -0.0001

Data Index: 517540 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9124. Min Act: -0.0001

Data Index: 127852 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1074870 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8821. Min Act: -0.0000

Data Index: 51915 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1034317 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1058832 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8705. Min Act: -0.0000

Data Index: 418557 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9186. Min Act: -0.0000

Data Index: 135140 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8555. Min Act: -0.0000

Data Index: 203911 (C4 (Web Text))

Max Activating Token Index: 49