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

Dataset: Open Web Text

Neuron 1926 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: 4.1919. Min Range: -4.1919

Max Act: 4.1919. Min Act: -0.1700

Data Index: 2902045 (Open Web Text)

Max Activating Token Index: 715

Text #1

Max Range: 4.1919. Min Range: -4.1919

Max Act: 4.0153. Min Act: -0.1700

Data Index: 8459990 (Open Web Text)

Max Activating Token Index: 244

Text #2

Max Range: 4.1919. Min Range: -4.1919

Max Act: 4.0060. Min Act: -0.1700

Data Index: 6962843 (Open Web Text)

Max Activating Token Index: 880

Text #3

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.9901. Min Act: -0.1700

Data Index: 7970541 (Open Web Text)

Max Activating Token Index: 349

Text #4

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.9608. Min Act: -0.1700

Data Index: 5397381 (Open Web Text)

Max Activating Token Index: 441

Text #5

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.9272. Min Act: -0.1700

Data Index: 1557501 (Open Web Text)

Max Activating Token Index: 72

Text #6

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.9558. Min Act: -0.1700

Data Index: 7820124 (Open Web Text)

Max Activating Token Index: 955

Text #7

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.9102. Min Act: -0.1700

Data Index: 7846919 (Open Web Text)

Max Activating Token Index: 529

Text #8

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.9285. Min Act: -0.1700

Data Index: 3280644 (Open Web Text)

Max Activating Token Index: 183

Text #9

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8635. Min Act: -0.1700

Data Index: 1394796 (Open Web Text)

Max Activating Token Index: 1000

Text #10

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8584. Min Act: -0.1700

Data Index: 1405482 (Open Web Text)

Max Activating Token Index: 853

Text #11

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8264. Min Act: -0.1700

Data Index: 4782360 (Open Web Text)

Max Activating Token Index: 713

Text #12

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8755. Min Act: -0.1700

Data Index: 6223171 (Open Web Text)

Max Activating Token Index: 95

Text #13

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8775. Min Act: -0.1700

Data Index: 1027250 (Open Web Text)

Max Activating Token Index: 429

Text #14

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8158. Min Act: -0.1700

Data Index: 7433662 (Open Web Text)

Max Activating Token Index: 960

Text #15

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8418. Min Act: -0.1700

Data Index: 6778803 (Open Web Text)

Max Activating Token Index: 682

Text #16

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8087. Min Act: -0.1700

Data Index: 366011 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8140. Min Act: -0.1700

Data Index: 2939878 (Open Web Text)

Max Activating Token Index: 709

Text #18

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8200. Min Act: -0.1700

Data Index: 2233840 (Open Web Text)

Max Activating Token Index: 60

Text #19

Max Range: 4.1919. Min Range: -4.1919

Max Act: 3.8298. Min Act: -0.1700

Data Index: 5044285 (Open Web Text)

Max Activating Token Index: 726