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

Dataset: Open Web Text

Neuron 2901 in Layer 5

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: 3.5518. Min Range: -3.5518

Max Act: 3.5518. Min Act: -0.1700

Data Index: 8042207 (Open Web Text)

Max Activating Token Index: 971

Text #1

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.5278. Min Act: -0.1700

Data Index: 7506856 (Open Web Text)

Max Activating Token Index: 580

Text #2

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.4594. Min Act: -0.1700

Data Index: 3687740 (Open Web Text)

Max Activating Token Index: 690

Text #3

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.4637. Min Act: -0.1700

Data Index: 4904723 (Open Web Text)

Max Activating Token Index: 982

Text #4

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.4749. Min Act: -0.1700

Data Index: 7415724 (Open Web Text)

Max Activating Token Index: 531

Text #5

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.4226. Min Act: -0.1700

Data Index: 4978414 (Open Web Text)

Max Activating Token Index: 230

Text #6

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.4122. Min Act: -0.1700

Data Index: 7919589 (Open Web Text)

Max Activating Token Index: 706

Text #7

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3892. Min Act: -0.1700

Data Index: 2756181 (Open Web Text)

Max Activating Token Index: 746

Text #8

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.4076. Min Act: -0.1700

Data Index: 6924545 (Open Web Text)

Max Activating Token Index: 941

Text #9

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3736. Min Act: -0.1700

Data Index: 8422904 (Open Web Text)

Max Activating Token Index: 761

Text #10

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3879. Min Act: -0.1700

Data Index: 4654160 (Open Web Text)

Max Activating Token Index: 942

Text #11

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3995. Min Act: -0.1700

Data Index: 7575950 (Open Web Text)

Max Activating Token Index: 789

Text #12

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3898. Min Act: -0.1700

Data Index: 5299875 (Open Web Text)

Max Activating Token Index: 804

Text #13

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3703. Min Act: -0.1700

Data Index: 8045409 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3614. Min Act: -0.1700

Data Index: 3243777 (Open Web Text)

Max Activating Token Index: 348

Text #15

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3907. Min Act: -0.1700

Data Index: 6775368 (Open Web Text)

Max Activating Token Index: 947

Text #16

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3305. Min Act: -0.1700

Data Index: 11343 (Open Web Text)

Max Activating Token Index: 384

Text #17

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3548. Min Act: -0.1700

Data Index: 3245791 (Open Web Text)

Max Activating Token Index: 466

Text #18

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3462. Min Act: -0.1700

Data Index: 6583160 (Open Web Text)

Max Activating Token Index: 330

Text #19

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3238. Min Act: -0.1700

Data Index: 4688143 (Open Web Text)

Max Activating Token Index: 711