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

Dataset: Open Web Text

Neuron 1267 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: 3.7993. Min Range: -3.7993

Max Act: 3.7993. Min Act: -0.1700

Data Index: 1034058 (Open Web Text)

Max Activating Token Index: 658

Text #1

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6934. Min Act: -0.1700

Data Index: 5902878 (Open Web Text)

Max Activating Token Index: 644

Text #2

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.7120. Min Act: -0.1700

Data Index: 2546933 (Open Web Text)

Max Activating Token Index: 912

Text #3

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6875. Min Act: -0.1700

Data Index: 3674572 (Open Web Text)

Max Activating Token Index: 214

Text #4

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6865. Min Act: -0.1700

Data Index: 7256234 (Open Web Text)

Max Activating Token Index: 846

Text #5

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6710. Min Act: -0.1700

Data Index: 7248139 (Open Web Text)

Max Activating Token Index: 580

Text #6

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6222. Min Act: -0.1700

Data Index: 5771793 (Open Web Text)

Max Activating Token Index: 255

Text #7

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6245. Min Act: -0.1700

Data Index: 2484788 (Open Web Text)

Max Activating Token Index: 398

Text #8

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6183. Min Act: -0.1700

Data Index: 6160479 (Open Web Text)

Max Activating Token Index: 824

Text #9

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6307. Min Act: -0.1700

Data Index: 7100353 (Open Web Text)

Max Activating Token Index: 656

Text #10

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6105. Min Act: -0.1700

Data Index: 8714263 (Open Web Text)

Max Activating Token Index: 616

Text #11

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5847. Min Act: -0.1700

Data Index: 404370 (Open Web Text)

Max Activating Token Index: 756

Text #12

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5835. Min Act: -0.1700

Data Index: 5815155 (Open Web Text)

Max Activating Token Index: 410

Text #13

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5697. Min Act: -0.1700

Data Index: 5587617 (Open Web Text)

Max Activating Token Index: 893

Text #14

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6052. Min Act: -0.1700

Data Index: 1679742 (Open Web Text)

Max Activating Token Index: 644

Text #15

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5990. Min Act: -0.1700

Data Index: 5425177 (Open Web Text)

Max Activating Token Index: 821

Text #16

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5999. Min Act: -0.1700

Data Index: 1703435 (Open Web Text)

Max Activating Token Index: 933

Text #17

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6161. Min Act: -0.1700

Data Index: 6910681 (Open Web Text)

Max Activating Token Index: 578

Text #18

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5938. Min Act: -0.1700

Data Index: 1361095 (Open Web Text)

Max Activating Token Index: 693

Text #19

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6257. Min Act: -0.1700

Data Index: 2190635 (Open Web Text)

Max Activating Token Index: 593