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

Dataset: Open Web Text

Neuron 1308 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: 3.6851. Min Range: -3.6851

Max Act: 3.6851. Min Act: -0.1700

Data Index: 973130 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.6822. Min Act: -0.1700

Data Index: 326807 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.6684. Min Act: -0.1700

Data Index: 1361978 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.6612. Min Act: -0.1700

Data Index: 3351249 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.6150. Min Act: -0.1700

Data Index: 8539359 (Open Web Text)

Max Activating Token Index: 22

Text #5

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.6365. Min Act: -0.1700

Data Index: 5874033 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.6308. Min Act: -0.1700

Data Index: 3995659 (Open Web Text)

Max Activating Token Index: 891

Text #7

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.6135. Min Act: -0.1700

Data Index: 4485039 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.6086. Min Act: -0.1700

Data Index: 8028153 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5633. Min Act: -0.1700

Data Index: 4225098 (Open Web Text)

Max Activating Token Index: 854

Text #10

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5529. Min Act: -0.1700

Data Index: 5237836 (Open Web Text)

Max Activating Token Index: 842

Text #11

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5798. Min Act: -0.1700

Data Index: 5562641 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5578. Min Act: -0.1700

Data Index: 452989 (Open Web Text)

Max Activating Token Index: 938

Text #13

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5728. Min Act: -0.1700

Data Index: 1176004 (Open Web Text)

Max Activating Token Index: 1015

Text #14

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5531. Min Act: -0.1700

Data Index: 6498431 (Open Web Text)

Max Activating Token Index: 199

Text #15

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5520. Min Act: -0.1700

Data Index: 6501380 (Open Web Text)

Max Activating Token Index: 931

Text #16

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5629. Min Act: -0.1700

Data Index: 6760062 (Open Web Text)

Max Activating Token Index: 773

Text #17

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5655. Min Act: -0.1700

Data Index: 1922131 (Open Web Text)

Max Activating Token Index: 1021

Text #18

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5922. Min Act: -0.1700

Data Index: 7207381 (Open Web Text)

Max Activating Token Index: 806

Text #19

Max Range: 3.6851. Min Range: -3.6851

Max Act: 3.5582. Min Act: -0.1700

Data Index: 7472185 (Open Web Text)

Max Activating Token Index: 33