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

Dataset: Open Web Text

Neuron 2483 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: 4.1278. Min Range: -4.1278

Max Act: 4.1278. Min Act: -0.1700

Data Index: 1961784 (Open Web Text)

Max Activating Token Index: 743

Text #1

Max Range: 4.1278. Min Range: -4.1278

Max Act: 4.0840. Min Act: -0.1700

Data Index: 6619537 (Open Web Text)

Max Activating Token Index: 102

Text #2

Max Range: 4.1278. Min Range: -4.1278

Max Act: 4.0548. Min Act: -0.1700

Data Index: 6771777 (Open Web Text)

Max Activating Token Index: 61

Text #3

Max Range: 4.1278. Min Range: -4.1278

Max Act: 4.0275. Min Act: -0.1700

Data Index: 5664444 (Open Web Text)

Max Activating Token Index: 161

Text #4

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.8649. Min Act: -0.1700

Data Index: 5520655 (Open Web Text)

Max Activating Token Index: 140

Text #5

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.8571. Min Act: -0.1700

Data Index: 155962 (Open Web Text)

Max Activating Token Index: 564

Text #6

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.8405. Min Act: -0.1700

Data Index: 6067255 (Open Web Text)

Max Activating Token Index: 109

Text #7

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.8197. Min Act: -0.1700

Data Index: 6642833 (Open Web Text)

Max Activating Token Index: 665

Text #8

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.8477. Min Act: -0.1700

Data Index: 4951803 (Open Web Text)

Max Activating Token Index: 350

Text #9

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.8125. Min Act: -0.1700

Data Index: 6642545 (Open Web Text)

Max Activating Token Index: 315

Text #10

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.7835. Min Act: -0.1700

Data Index: 8012319 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.7738. Min Act: -0.1700

Data Index: 4193459 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.7458. Min Act: -0.1700

Data Index: 3036214 (Open Web Text)

Max Activating Token Index: 44

Text #13

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.7095. Min Act: -0.1700

Data Index: 7549311 (Open Web Text)

Max Activating Token Index: 191

Text #14

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.6925. Min Act: -0.1700

Data Index: 1704424 (Open Web Text)

Max Activating Token Index: 95

Text #15

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.6628. Min Act: -0.1700

Data Index: 7347943 (Open Web Text)

Max Activating Token Index: 354

Text #16

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.6173. Min Act: -0.1700

Data Index: 5046608 (Open Web Text)

Max Activating Token Index: 961

Text #17

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.6737. Min Act: -0.1700

Data Index: 1917413 (Open Web Text)

Max Activating Token Index: 138

Text #18

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.6714. Min Act: -0.1700

Data Index: 8261461 (Open Web Text)

Max Activating Token Index: 670

Text #19

Max Range: 4.1278. Min Range: -4.1278

Max Act: 3.6005. Min Act: -0.1700

Data Index: 1874169 (Open Web Text)

Max Activating Token Index: 945