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

Dataset: Open Web Text

Neuron 2129 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: 3.6974. Min Range: -3.6974

Max Act: 3.6872. Min Act: -0.1700

Data Index: 8268710 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6974. Min Act: -0.1700

Data Index: 7932908 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6614. Min Act: -0.1700

Data Index: 2588165 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6296. Min Act: -0.1700

Data Index: 7927569 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6264. Min Act: -0.1700

Data Index: 8587122 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6162. Min Act: -0.1700

Data Index: 3647375 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6130. Min Act: -0.1700

Data Index: 3960029 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6139. Min Act: -0.1700

Data Index: 1944390 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6109. Min Act: -0.1700

Data Index: 6408176 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6139. Min Act: -0.1700

Data Index: 2413855 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5854. Min Act: -0.1700

Data Index: 6825399 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6067. Min Act: -0.1700

Data Index: 856806 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5950. Min Act: -0.1700

Data Index: 2188334 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5697. Min Act: -0.1700

Data Index: 8314558 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5724. Min Act: -0.1700

Data Index: 6140798 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5486. Min Act: -0.1700

Data Index: 5011970 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5669. Min Act: -0.1700

Data Index: 7516051 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5730. Min Act: -0.1700

Data Index: 7448509 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5447. Min Act: -0.1700

Data Index: 3804090 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.5652. Min Act: -0.1700

Data Index: 7326868 (Open Web Text)

Max Activating Token Index: 3