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

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

Neuron 1255 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: 1.7979. Min Range: -1.7979

Max Act: 1.7979. Min Act: -0.0000

Data Index: 492768 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.4245. Min Act: -0.0000

Data Index: 237771 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.4969. Min Act: -0.0000

Data Index: 689795 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.3067. Min Act: -0.0000

Data Index: 206131 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.2577. Min Act: -0.0000

Data Index: 772598 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.0961. Min Act: -0.0000

Data Index: 475896 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.0152. Min Act: -0.0000

Data Index: 303740 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.1659. Min Act: -0.0000

Data Index: 137067 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.1182. Min Act: -0.0000

Data Index: 471193 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.0285. Min Act: -0.0000

Data Index: 392253 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.0096. Min Act: -0.0000

Data Index: 13540 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1281969 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.0030. Min Act: -0.0000

Data Index: 892150 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.0015. Min Act: -0.0000

Data Index: 200102 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 1.7979. Min Range: -1.7979

Max Act: 0.9397. Min Act: -0.0000

Data Index: 182714 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 1.7979. Min Range: -1.7979

Max Act: 0.9937. Min Act: -0.0000

Data Index: 784107 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.0554. Min Act: -0.0000

Data Index: 66431 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 1.7979. Min Range: -1.7979

Max Act: 1.0435. Min Act: -0.0000

Data Index: 678491 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 1.7979. Min Range: -1.7979

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1009857 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 1.7979. Min Range: -1.7979

Max Act: 0.9781. Min Act: -0.0000

Data Index: 508960 (C4 (Web Text))

Max Activating Token Index: 325