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

Dataset: Open Web Text

Neuron 1853 in Layer 3

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: 3.3172. Min Range: -3.3172

Max Act: 3.3172. Min Act: -0.1700

Data Index: 4188469 (Open Web Text)

Max Activating Token Index: 907

Text #1

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2458. Min Act: -0.1700

Data Index: 41124 (Open Web Text)

Max Activating Token Index: 210

Text #2

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2298. Min Act: -0.1700

Data Index: 6038785 (Open Web Text)

Max Activating Token Index: 612

Text #3

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2376. Min Act: -0.1700

Data Index: 3559161 (Open Web Text)

Max Activating Token Index: 762

Text #4

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2005. Min Act: -0.1700

Data Index: 5152293 (Open Web Text)

Max Activating Token Index: 679

Text #5

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.1186. Min Act: -0.1700

Data Index: 5392150 (Open Web Text)

Max Activating Token Index: 562

Text #6

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.1040. Min Act: -0.1700

Data Index: 5917637 (Open Web Text)

Max Activating Token Index: 186

Text #7

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.0786. Min Act: -0.1700

Data Index: 2070426 (Open Web Text)

Max Activating Token Index: 382

Text #8

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.0742. Min Act: -0.1700

Data Index: 5827588 (Open Web Text)

Max Activating Token Index: 568

Text #9

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.0626. Min Act: -0.1700

Data Index: 2779034 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.0222. Min Act: -0.1700

Data Index: 3997964 (Open Web Text)

Max Activating Token Index: 845

Text #11

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.0132. Min Act: -0.1700

Data Index: 2942852 (Open Web Text)

Max Activating Token Index: 48

Text #12

Max Range: 3.3172. Min Range: -3.3172

Max Act: 2.9891. Min Act: -0.1700

Data Index: 5205596 (Open Web Text)

Max Activating Token Index: 858

Text #13

Max Range: 3.3172. Min Range: -3.3172

Max Act: 2.9644. Min Act: -0.1700

Data Index: 7997924 (Open Web Text)

Max Activating Token Index: 855

Text #14

Max Range: 3.3172. Min Range: -3.3172

Max Act: 2.9914. Min Act: -0.1700

Data Index: 2100734 (Open Web Text)

Max Activating Token Index: 83

Text #15

Max Range: 3.3172. Min Range: -3.3172

Max Act: 2.9785. Min Act: -0.1700

Data Index: 900028 (Open Web Text)

Max Activating Token Index: 383

Text #16

Max Range: 3.3172. Min Range: -3.3172

Max Act: 2.9570. Min Act: -0.1700

Data Index: 8236406 (Open Web Text)

Max Activating Token Index: 112

Text #17

Max Range: 3.3172. Min Range: -3.3172

Max Act: 2.9628. Min Act: -0.1700

Data Index: 6020446 (Open Web Text)

Max Activating Token Index: 973

Text #18

Max Range: 3.3172. Min Range: -3.3172

Max Act: 2.9562. Min Act: -0.1700

Data Index: 8383717 (Open Web Text)

Max Activating Token Index: 840

Text #19

Max Range: 3.3172. Min Range: -3.3172

Max Act: 2.9635. Min Act: -0.1700

Data Index: 692743 (Open Web Text)

Max Activating Token Index: 199