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

Dataset: Open Web Text

Neuron 272 in Layer 3

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: 2.4932. Min Range: -2.4932

Max Act: 2.4932. Min Act: -0.1700

Data Index: 2135168 (Open Web Text)

Max Activating Token Index: 611

Text #1

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.4520. Min Act: -0.1700

Data Index: 5058702 (Open Web Text)

Max Activating Token Index: 524

Text #2

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.4543. Min Act: -0.1700

Data Index: 7276686 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.4057. Min Act: -0.1700

Data Index: 7109310 (Open Web Text)

Max Activating Token Index: 702

Text #4

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.4109. Min Act: -0.1700

Data Index: 7861033 (Open Web Text)

Max Activating Token Index: 147

Text #5

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3868. Min Act: -0.1700

Data Index: 65387 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3971. Min Act: -0.1700

Data Index: 7048373 (Open Web Text)

Max Activating Token Index: 443

Text #7

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3894. Min Act: -0.1700

Data Index: 4847503 (Open Web Text)

Max Activating Token Index: 817

Text #8

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3701. Min Act: -0.1700

Data Index: 2107440 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3472. Min Act: -0.1700

Data Index: 3292360 (Open Web Text)

Max Activating Token Index: 834

Text #10

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3591. Min Act: -0.1700

Data Index: 1479777 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3591. Min Act: -0.1700

Data Index: 7047425 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3591. Min Act: -0.1700

Data Index: 4012821 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3591. Min Act: -0.1700

Data Index: 2031771 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3591. Min Act: -0.1700

Data Index: 6445414 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3591. Min Act: -0.1700

Data Index: 3689973 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3591. Min Act: -0.1700

Data Index: 6168074 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3591. Min Act: -0.1700

Data Index: 8186356 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3591. Min Act: -0.1700

Data Index: 5590089 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.4932. Min Range: -2.4932

Max Act: 2.3551. Min Act: -0.1700

Data Index: 6925610 (Open Web Text)

Max Activating Token Index: 4