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

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

Neuron 4650 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1136. Min Range: -3.1136

Max Act: 2.9569. Min Act: -0.0000

Data Index: 143554 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 3.1136. Min Range: -3.1136

Max Act: 3.1136. Min Act: -0.0000

Data Index: 522365 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 3.1136. Min Range: -3.1136

Max Act: 3.0045. Min Act: -0.0000

Data Index: 532350 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 3.1136. Min Range: -3.1136

Max Act: 2.6518. Min Act: -0.0000

Data Index: 889921 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 3.1136. Min Range: -3.1136

Max Act: 2.4426. Min Act: -0.0000

Data Index: 490264 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 3.1136. Min Range: -3.1136

Max Act: 2.5540. Min Act: -0.0000

Data Index: 522834 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 3.1136. Min Range: -3.1136

Max Act: 2.2724. Min Act: -0.0000

Data Index: 1146921 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 3.1136. Min Range: -3.1136

Max Act: 2.0893. Min Act: -0.0000

Data Index: 238307 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 3.1136. Min Range: -3.1136

Max Act: 2.2097. Min Act: -0.0000

Data Index: 191848 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 3.1136. Min Range: -3.1136

Max Act: 2.1879. Min Act: -0.0001

Data Index: 1191309 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 3.1136. Min Range: -3.1136

Max Act: 2.0618. Min Act: -0.0000

Data Index: 267698 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 3.1136. Min Range: -3.1136

Max Act: 2.0055. Min Act: -0.0000

Data Index: 270800 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 3.1136. Min Range: -3.1136

Max Act: 1.8595. Min Act: -0.0001

Data Index: 743240 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 3.1136. Min Range: -3.1136

Max Act: 1.8650. Min Act: -0.0000

Data Index: 957073 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 3.1136. Min Range: -3.1136

Max Act: 1.7979. Min Act: -0.0000

Data Index: 811497 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 3.1136. Min Range: -3.1136

Max Act: 1.5006. Min Act: -0.0000

Data Index: 806171 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 3.1136. Min Range: -3.1136

Max Act: 1.7364. Min Act: -0.0000

Data Index: 1058270 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 3.1136. Min Range: -3.1136

Max Act: 1.9091. Min Act: -0.0001

Data Index: 135378 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 3.1136. Min Range: -3.1136

Max Act: 2.0096. Min Act: -0.0000

Data Index: 1021052 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 3.1136. Min Range: -3.1136

Max Act: 1.7127. Min Act: -0.0000

Data Index: 612956 (C4 (Web Text))

Max Activating Token Index: 667