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

Dataset: Open Web Text

Neuron 2332 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: 3.0825. Min Range: -3.0825

Max Act: 3.0825. Min Act: -0.1700

Data Index: 6112946 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.0825. Min Range: -3.0825

Max Act: 3.0374. Min Act: -0.1700

Data Index: 8313457 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.0825. Min Range: -3.0825

Max Act: 3.0410. Min Act: -0.1700

Data Index: 4136652 (Open Web Text)

Max Activating Token Index: 65

Text #3

Max Range: 3.0825. Min Range: -3.0825

Max Act: 3.0128. Min Act: -0.1700

Data Index: 6234459 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.0825. Min Range: -3.0825

Max Act: 3.0128. Min Act: -0.1700

Data Index: 440664 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.0825. Min Range: -3.0825

Max Act: 3.0290. Min Act: -0.1700

Data Index: 4754805 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.0825. Min Range: -3.0825

Max Act: 3.0059. Min Act: -0.1700

Data Index: 4453253 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.0825. Min Range: -3.0825

Max Act: 3.0048. Min Act: -0.1700

Data Index: 8088644 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9955. Min Act: -0.1700

Data Index: 1818886 (Open Web Text)

Max Activating Token Index: 1007

Text #9

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9780. Min Act: -0.1700

Data Index: 885631 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9784. Min Act: -0.1700

Data Index: 7684910 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9784. Min Act: -0.1700

Data Index: 7272279 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9784. Min Act: -0.1700

Data Index: 3719124 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9784. Min Act: -0.1700

Data Index: 5820443 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9784. Min Act: -0.1700

Data Index: 616163 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9818. Min Act: -0.1700

Data Index: 3036650 (Open Web Text)

Max Activating Token Index: 844

Text #16

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9784. Min Act: -0.1700

Data Index: 5706110 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9881. Min Act: -0.1700

Data Index: 5777104 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9791. Min Act: -0.1700

Data Index: 6143288 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9784. Min Act: -0.1700

Data Index: 2020254 (Open Web Text)

Max Activating Token Index: 2