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

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

Neuron 4370 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.8853. Min Act: -0.0000

Data Index: 144664 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.8254. Min Act: -0.0000

Data Index: 192165 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.7476. Min Act: -0.0000

Data Index: 1289167 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.4036. Min Act: -0.0000

Data Index: 745672 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.4279. Min Act: -0.0000

Data Index: 1107762 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.5752. Min Act: -0.0000

Data Index: 93760 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.3790. Min Act: -0.0000

Data Index: 714167 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.3040. Min Act: -0.0000

Data Index: 423362 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.2092. Min Act: -0.0000

Data Index: 133893 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1133485 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.1953. Min Act: -0.0000

Data Index: 843153 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1016805 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.2447. Min Act: -0.0000

Data Index: 118202 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.2490. Min Act: -0.0000

Data Index: 113460 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.1815. Min Act: -0.0000

Data Index: 518387 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.2134. Min Act: -0.0000

Data Index: 717319 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.1196. Min Act: -0.0000

Data Index: 665886 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.1107. Min Act: -0.0000

Data Index: 174018 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.0525. Min Act: -0.0000

Data Index: 147166 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.0931. Min Act: -0.0000

Data Index: 588292 (C4 (Web Text))

Max Activating Token Index: 611