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

Dataset: Open Web Text

Neuron 2676 in Layer 2

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: 3.2223. Min Range: -3.2223

Max Act: 3.2223. Min Act: -0.1700

Data Index: 6874373 (Open Web Text)

Max Activating Token Index: 132

Text #1

Max Range: 3.2223. Min Range: -3.2223

Max Act: 3.0913. Min Act: -0.1700

Data Index: 7999682 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.2223. Min Range: -3.2223

Max Act: 3.0860. Min Act: -0.1700

Data Index: 2321048 (Open Web Text)

Max Activating Token Index: 312

Text #3

Max Range: 3.2223. Min Range: -3.2223

Max Act: 3.0753. Min Act: -0.1700

Data Index: 1394038 (Open Web Text)

Max Activating Token Index: 869

Text #4

Max Range: 3.2223. Min Range: -3.2223

Max Act: 3.0625. Min Act: -0.1700

Data Index: 386647 (Open Web Text)

Max Activating Token Index: 809

Text #5

Max Range: 3.2223. Min Range: -3.2223

Max Act: 3.0398. Min Act: -0.1700

Data Index: 2425232 (Open Web Text)

Max Activating Token Index: 252

Text #6

Max Range: 3.2223. Min Range: -3.2223

Max Act: 3.0310. Min Act: -0.1700

Data Index: 8445897 (Open Web Text)

Max Activating Token Index: 734

Text #7

Max Range: 3.2223. Min Range: -3.2223

Max Act: 3.0256. Min Act: -0.1700

Data Index: 4243070 (Open Web Text)

Max Activating Token Index: 691

Text #8

Max Range: 3.2223. Min Range: -3.2223

Max Act: 3.0046. Min Act: -0.1700

Data Index: 2356630 (Open Web Text)

Max Activating Token Index: 65

Text #9

Max Range: 3.2223. Min Range: -3.2223

Max Act: 3.0092. Min Act: -0.1700

Data Index: 4919094 (Open Web Text)

Max Activating Token Index: 77

Text #10

Max Range: 3.2223. Min Range: -3.2223

Max Act: 3.0222. Min Act: -0.1700

Data Index: 6854005 (Open Web Text)

Max Activating Token Index: 50

Text #11

Max Range: 3.2223. Min Range: -3.2223

Max Act: 2.9808. Min Act: -0.1700

Data Index: 16160 (Open Web Text)

Max Activating Token Index: 95

Text #12

Max Range: 3.2223. Min Range: -3.2223

Max Act: 3.0052. Min Act: -0.1700

Data Index: 2734483 (Open Web Text)

Max Activating Token Index: 796

Text #13

Max Range: 3.2223. Min Range: -3.2223

Max Act: 2.9740. Min Act: -0.1700

Data Index: 5250455 (Open Web Text)

Max Activating Token Index: 572

Text #14

Max Range: 3.2223. Min Range: -3.2223

Max Act: 2.9886. Min Act: -0.1700

Data Index: 1099894 (Open Web Text)

Max Activating Token Index: 122

Text #15

Max Range: 3.2223. Min Range: -3.2223

Max Act: 3.0033. Min Act: -0.1700

Data Index: 5014574 (Open Web Text)

Max Activating Token Index: 926

Text #16

Max Range: 3.2223. Min Range: -3.2223

Max Act: 2.9806. Min Act: -0.1700

Data Index: 4891765 (Open Web Text)

Max Activating Token Index: 792

Text #17

Max Range: 3.2223. Min Range: -3.2223

Max Act: 2.9833. Min Act: -0.1700

Data Index: 3072239 (Open Web Text)

Max Activating Token Index: 110

Text #18

Max Range: 3.2223. Min Range: -3.2223

Max Act: 2.9663. Min Act: -0.1700

Data Index: 6473104 (Open Web Text)

Max Activating Token Index: 104

Text #19

Max Range: 3.2223. Min Range: -3.2223

Max Act: 2.9805. Min Act: -0.1700

Data Index: 5105104 (Open Web Text)

Max Activating Token Index: 240