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

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

Neuron 2401 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: 1.3139. Min Range: -1.3139

Max Act: 1.2622. Min Act: -0.0000

Data Index: 581991 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 1.3139. Min Range: -1.3139

Max Act: 1.3139. Min Act: -0.0000

Data Index: 333338 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 1.3139. Min Range: -1.3139

Max Act: 1.1242. Min Act: -0.0000

Data Index: 7389 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.3139. Min Range: -1.3139

Max Act: 1.0750. Min Act: -0.0000

Data Index: 1158787 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 1.3139. Min Range: -1.3139

Max Act: 1.1083. Min Act: -0.0000

Data Index: 932766 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9535. Min Act: -0.0000

Data Index: 714799 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9343. Min Act: -0.0000

Data Index: 344536 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.8892. Min Act: -0.0000

Data Index: 893302 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1103519 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1102496 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9973. Min Act: -0.0000

Data Index: 942833 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1097309 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.8273. Min Act: -0.0000

Data Index: 1294271 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.8566. Min Act: -0.0000

Data Index: 90052 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.8627. Min Act: -0.0000

Data Index: 70903 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.7924. Min Act: -0.0000

Data Index: 575012 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1089585 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1285514 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.7273. Min Act: -0.0000

Data Index: 395750 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.7552. Min Act: -0.0000

Data Index: 669099 (C4 (Web Text))

Max Activating Token Index: 723