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

Dataset: Open Web Text

Neuron 3061 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: 3.6639. Min Range: -3.6639

Max Act: 3.6639. Min Act: -0.1700

Data Index: 6561326 (Open Web Text)

Max Activating Token Index: 615

Text #1

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5900. Min Act: -0.1700

Data Index: 3909852 (Open Web Text)

Max Activating Token Index: 808

Text #2

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.6413. Min Act: -0.1700

Data Index: 6726449 (Open Web Text)

Max Activating Token Index: 433

Text #3

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5804. Min Act: -0.1700

Data Index: 7125610 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5963. Min Act: -0.1700

Data Index: 7163665 (Open Web Text)

Max Activating Token Index: 799

Text #5

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5847. Min Act: -0.1700

Data Index: 3653956 (Open Web Text)

Max Activating Token Index: 949

Text #6

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5461. Min Act: -0.1700

Data Index: 1798066 (Open Web Text)

Max Activating Token Index: 969

Text #7

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5186. Min Act: -0.1700

Data Index: 5308742 (Open Web Text)

Max Activating Token Index: 805

Text #8

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5684. Min Act: -0.1700

Data Index: 3652281 (Open Web Text)

Max Activating Token Index: 1009

Text #9

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5205. Min Act: -0.1700

Data Index: 3269866 (Open Web Text)

Max Activating Token Index: 564

Text #10

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5033. Min Act: -0.1700

Data Index: 7805074 (Open Web Text)

Max Activating Token Index: 726

Text #11

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.4940. Min Act: -0.1700

Data Index: 7649371 (Open Web Text)

Max Activating Token Index: 720

Text #12

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5465. Min Act: -0.1700

Data Index: 7438872 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.4969. Min Act: -0.1700

Data Index: 5573698 (Open Web Text)

Max Activating Token Index: 1005

Text #14

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.4846. Min Act: -0.1700

Data Index: 2790507 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5228. Min Act: -0.1700

Data Index: 1243219 (Open Web Text)

Max Activating Token Index: 997

Text #16

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.4996. Min Act: -0.1700

Data Index: 7102221 (Open Web Text)

Max Activating Token Index: 115

Text #17

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5034. Min Act: -0.1700

Data Index: 3600875 (Open Web Text)

Max Activating Token Index: 855

Text #18

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5172. Min Act: -0.1700

Data Index: 4009955 (Open Web Text)

Max Activating Token Index: 649

Text #19

Max Range: 3.6639. Min Range: -3.6639

Max Act: 3.5000. Min Act: -0.1700

Data Index: 2136060 (Open Web Text)

Max Activating Token Index: 362