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

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

Neuron 5405 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: 2.4734. Min Range: -2.4734

Max Act: 2.4734. Min Act: -0.0000

Data Index: 774206 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 2.4734. Min Range: -2.4734

Max Act: 2.1484. Min Act: -0.0000

Data Index: 745571 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.8780. Min Act: -0.0000

Data Index: 769502 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.8765. Min Act: -0.0000

Data Index: 797112 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.8330. Min Act: -0.0000

Data Index: 362285 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.6201. Min Act: -0.0000

Data Index: 1091834 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.7397. Min Act: -0.0000

Data Index: 1022817 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.6913. Min Act: -0.0000

Data Index: 1078399 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.6016. Min Act: -0.0000

Data Index: 1054246 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.6151. Min Act: -0.0000

Data Index: 1337117 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.5774. Min Act: -0.0000

Data Index: 110731 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.5741. Min Act: -0.0000

Data Index: 309497 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.5845. Min Act: -0.0000

Data Index: 51028 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.4659. Min Act: -0.0000

Data Index: 33507 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.5565. Min Act: -0.0000

Data Index: 29483 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.4467. Min Act: -0.0000

Data Index: 876459 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.4870. Min Act: -0.0000

Data Index: 885501 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.3188. Min Act: -0.0000

Data Index: 810790 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.3798. Min Act: -0.0000

Data Index: 646134 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.3551. Min Act: -0.0000

Data Index: 284590 (C4 (Web Text))

Max Activating Token Index: 856