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

Dataset: Open Web Text

Neuron 2122 in Layer 0

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: 2.8855. Min Range: -2.8855

Max Act: 2.8855. Min Act: -0.1700

Data Index: 4830987 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.8259. Min Act: -0.1700

Data Index: 4237512 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.8338. Min Act: -0.1700

Data Index: 3028817 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.8287. Min Act: -0.1700

Data Index: 8712338 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.8102. Min Act: -0.1700

Data Index: 4367306 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.8106. Min Act: -0.1700

Data Index: 4011916 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7925. Min Act: -0.1700

Data Index: 6527695 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7761. Min Act: -0.1700

Data Index: 7431546 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7600. Min Act: -0.1700

Data Index: 2470129 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7633. Min Act: -0.1700

Data Index: 4163830 (Open Web Text)

Max Activating Token Index: 32

Text #10

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7677. Min Act: -0.1700

Data Index: 8349335 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7608. Min Act: -0.1700

Data Index: 8165742 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7624. Min Act: -0.1700

Data Index: 8042480 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7649. Min Act: -0.1700

Data Index: 1319276 (Open Web Text)

Max Activating Token Index: 58

Text #14

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7703. Min Act: -0.1700

Data Index: 1803937 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7689. Min Act: -0.1700

Data Index: 625738 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7470. Min Act: -0.1700

Data Index: 2112023 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7470. Min Act: -0.1700

Data Index: 5220999 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7513. Min Act: -0.1700

Data Index: 4207612 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.8855. Min Range: -2.8855

Max Act: 2.7470. Min Act: -0.1700

Data Index: 5231439 (Open Web Text)

Max Activating Token Index: 3