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

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

Neuron 48 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.1591. Min Act: -0.0000

Data Index: 463008 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.1408. Min Act: -0.0000

Data Index: 553518 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.1158. Min Act: -0.0000

Data Index: 78478 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.1252. Min Act: -0.0000

Data Index: 287113 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.0741. Min Act: -0.0000

Data Index: 279052 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.0728. Min Act: -0.0000

Data Index: 495718 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.0707. Min Act: -0.0000

Data Index: 1008415 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.0341. Min Act: -0.0000

Data Index: 718661 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 1.1591. Min Range: -1.1591

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1106744 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.0342. Min Act: -0.0000

Data Index: 1329632 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 1.1591. Min Range: -1.1591

Max Act: 0.9548. Min Act: -0.0000

Data Index: 405233 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.0322. Min Act: -0.0000

Data Index: 282913 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.0012. Min Act: -0.0000

Data Index: 775731 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.0511. Min Act: -0.0000

Data Index: 193498 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.0215. Min Act: -0.0000

Data Index: 663779 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 1.1591. Min Range: -1.1591

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1035832 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 1.1591. Min Range: -1.1591

Max Act: 0.9999. Min Act: -0.0000

Data Index: 471252 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1255102 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 1.1591. Min Range: -1.1591

Max Act: 0.9547. Min Act: -0.0000

Data Index: 795792 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.1591. Min Range: -1.1591

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1325298 (C4 (Web Text))

Max Activating Token Index: 890