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

Dataset: Open Web Text

Neuron 523 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: 4.0839. Min Range: -4.0839

Max Act: 4.0839. Min Act: -0.1700

Data Index: 7276086 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.0839. Min Range: -4.0839

Max Act: 4.0127. Min Act: -0.1700

Data Index: 7551314 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9824. Min Act: -0.1700

Data Index: 5407219 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9795. Min Act: -0.1700

Data Index: 8151713 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9442. Min Act: -0.1700

Data Index: 7880300 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9424. Min Act: -0.1700

Data Index: 3734200 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9406. Min Act: -0.1700

Data Index: 6404204 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9579. Min Act: -0.1700

Data Index: 6195075 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9483. Min Act: -0.1700

Data Index: 2492096 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9449. Min Act: -0.1700

Data Index: 510303 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9524. Min Act: -0.1700

Data Index: 5262960 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9176. Min Act: -0.1700

Data Index: 6144339 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9310. Min Act: -0.1700

Data Index: 8144864 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9137. Min Act: -0.1700

Data Index: 5686380 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9418. Min Act: -0.1700

Data Index: 3218131 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9258. Min Act: -0.1700

Data Index: 1717718 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9168. Min Act: -0.1700

Data Index: 1232804 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.8974. Min Act: -0.1700

Data Index: 3174797 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.9042. Min Act: -0.1700

Data Index: 2174303 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 4.0839. Min Range: -4.0839

Max Act: 3.8942. Min Act: -0.1700

Data Index: 3868504 (Open Web Text)

Max Activating Token Index: 4