Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2491 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.0766. Min Range: -5.0766

Max Act: 5.0766. Min Act: -0.1700

Data Index: 3963422 (Open Web Text)

Max Activating Token Index: 209

Text #1

Max Range: 5.0766. Min Range: -5.0766

Max Act: 5.0119. Min Act: -0.1700

Data Index: 2977791 (Open Web Text)

Max Activating Token Index: 814

Text #2

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.8705. Min Act: -0.1700

Data Index: 4340283 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.8794. Min Act: -0.1700

Data Index: 8751109 (Open Web Text)

Max Activating Token Index: 794

Text #4

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.8381. Min Act: -0.1700

Data Index: 4629292 (Open Web Text)

Max Activating Token Index: 429

Text #5

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.7835. Min Act: -0.1700

Data Index: 4597634 (Open Web Text)

Max Activating Token Index: 89

Text #6

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.7431. Min Act: -0.1700

Data Index: 8604137 (Open Web Text)

Max Activating Token Index: 851

Text #7

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.7778. Min Act: -0.1700

Data Index: 2842118 (Open Web Text)

Max Activating Token Index: 751

Text #8

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.7598. Min Act: -0.1700

Data Index: 5223942 (Open Web Text)

Max Activating Token Index: 715

Text #9

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.7385. Min Act: -0.1700

Data Index: 99276 (Open Web Text)

Max Activating Token Index: 923

Text #10

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.6907. Min Act: -0.1700

Data Index: 6064810 (Open Web Text)

Max Activating Token Index: 847

Text #11

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.6709. Min Act: -0.1700

Data Index: 3703464 (Open Web Text)

Max Activating Token Index: 208

Text #12

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.6958. Min Act: -0.1700

Data Index: 5850561 (Open Web Text)

Max Activating Token Index: 273

Text #13

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.6763. Min Act: -0.1700

Data Index: 6524310 (Open Web Text)

Max Activating Token Index: 716

Text #14

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.6598. Min Act: -0.1700

Data Index: 2534761 (Open Web Text)

Max Activating Token Index: 848

Text #15

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.6719. Min Act: -0.1700

Data Index: 7146758 (Open Web Text)

Max Activating Token Index: 812

Text #16

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.5753. Min Act: -0.1700

Data Index: 7812460 (Open Web Text)

Max Activating Token Index: 459

Text #17

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.6202. Min Act: -0.1700

Data Index: 4399086 (Open Web Text)

Max Activating Token Index: 809

Text #18

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.5980. Min Act: -0.1700

Data Index: 80902 (Open Web Text)

Max Activating Token Index: 434

Text #19

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.6164. Min Act: -0.1700

Data Index: 2091446 (Open Web Text)

Max Activating Token Index: 333